{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T01:43:14Z","timestamp":1770255794855,"version":"3.49.0"},"reference-count":214,"publisher":"Association for Computing Machinery (ACM)","issue":"7","funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC3305404"],"award-info":[{"award-number":["2023YFC3305404"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U23A20307"],"award-info":[{"award-number":["U23A20307"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>State-of-the-art watermarking and fingerprinting techniques for Large Language Models (LLMs) are explored, with our analysis spanning a wide array of methodologies designed to protect the intellectual property of LLMs. The review of watermarking techniques is based on embedding watermarks during the training, logits generation, and token sampling phases. Meanwhile, we investigate the application of watermarking technology in multimodal LLMs and potential attacks on watermarks. Moreover, our examination of fingerprinting techniques revealed the ingenuity behind methods used to identify LLMs. We discussed the development of fingerprints based on model behavior and using deep learning models to learn thresholds for fingerprint comparison. Our survey has underscored the importance of advancing security measures for LLMs, especially in light of the increasing sophistication of adversarial attacks. As LLMs continue to play a pivotal role in advancing AI technologies, developing and refining security measures that safeguard their intellectual property and ensure their ethical deployment is imperative.<\/jats:p>","DOI":"10.1145\/3773028","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T22:40:58Z","timestamp":1764974458000},"page":"1-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Securing Large Language Models: A Survey of Watermarking and Fingerprinting Techniques"],"prefix":"10.1145","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9570-7566","authenticated-orcid":false,"given":"Peigen","family":"Ye","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5823-8343","authenticated-orcid":false,"given":"Huali","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Cyberspace Security, Guangzhou University","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1534-3658","authenticated-orcid":false,"given":"Zhengdao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Guangzhou University","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2854-2931","authenticated-orcid":false,"given":"Anli","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Guangzhou University","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1493-9671","authenticated-orcid":false,"given":"Hongyang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Guangzhou University","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1577-1193","authenticated-orcid":false,"given":"Shaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Guangzhou University","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1279-3418","authenticated-orcid":false,"given":"Jin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Guangzhou University","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,4]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/SP40001.2021.00083","volume-title":"Proceedings of the 2021 IEEE Symposium on Security and Privacy","author":"Abdelnabi Sahar","year":"2021","unstructured":"Sahar Abdelnabi and Mario Fritz. 2021. Adversarial watermarking transformer: Towards tracing text provenance with data hiding. In Proceedings of the 2021 IEEE Symposium on Security and Privacy. IEEE, 121\u2013140."},{"key":"e_1_3_1_3_2","first-page":"181","volume-title":"Proceedings of the 3rd Workshop on Natural Language Generation, Evaluation, and Metrics","author":"Abdullin Yelaman","year":"2023","unstructured":"Yelaman Abdullin, Diego Molla, Bahadorreza Ofoghi, et\u00a0al. 2023. Synthetic dialogue dataset generation using LLM agents. In Proceedings of the 3rd Workshop on Natural Language Generation, Evaluation, and Metrics. 181\u2013191."},{"issue":"2","key":"e_1_3_1_4_2","doi-asserted-by":"crossref","first-page":"5531","DOI":"10.1007\/s11042-023-15806-y","article-title":"Digital image and video watermarking: methodologies, attacks, applications, and future directions","volume":"83","author":"Aberna P.","year":"2024","unstructured":"P. Aberna and L. Agilandeeswari. 2024. Digital image and video watermarking: methodologies, attacks, applications, and future directions. Multimedia Tools and Applications 83, 2 (2024), 5531\u20135591.","journal-title":"Multimedia Tools and Applications"},{"key":"e_1_3_1_5_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal et\u00a0al. 2023. GPT-4 Technical Report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_1_6_2","unstructured":"Anirudh Ajith Sameer Singh and Danish Pruthi. 2023. Performance trade-offs of watermarking large language models. arXiv:2311.09816. Retrieved from https:\/\/arxiv.org\/abs\/2311.09816"},{"key":"e_1_3_1_7_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems","author":"Andriushchenko Maksym","year":"2020","unstructured":"Maksym Andriushchenko and Nicolas Flammarion. 2020. Understanding and improving fast adversarial training. In Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_8_2","first-page":"38176","volume-title":"Proceedings of the Advances in Neural Information Processing Systems.","volume":"35","author":"Bakker Michiel","year":"2022","unstructured":"Michiel Bakker, Martin Chadwick, Hannah Sheahan, et\u00a0al. 2022. Fine-tuning language models to find agreement among humans with diverse preferences. In Proceedings of the Advances in Neural Information Processing Systems.S. Koyejo, S. Mohamed, A. Agarwal, et\u00a0al. (Eds.), Vol. 35, 38176\u201338189."},{"key":"e_1_3_1_9_2","first-page":"4625","volume-title":"Proceedings of the ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Baldassini Folco Bertini","year":"2024","unstructured":"Folco Bertini Baldassini, Huy H. Nguyen, Ching-Chung Chang, et\u00a0al. 2024. Cross-attention watermarking of large language models. In Proceedings of the ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 4625\u20134629."},{"key":"e_1_3_1_10_2","unstructured":"Lewis Birch William Hackett Stefan Trawicki et\u00a0al. 2023. Model leeching: An extraction attack targeting llms. arXiv:2309.10544. Retrieved from https:\/\/arxiv.org\/abs\/2309.10544"},{"key":"e_1_3_1_11_2","first-page":"14","volume-title":"Proceedings of the 2021 ACM Asia Conference on Computer and Communications Security","author":"Cao Xiaoyu","year":"2021","unstructured":"Xiaoyu Cao, Jinyuan Jia, and Neil Zhenqiang Gong. 2021. IPGuard: Protecting intellectual property of deep neural networks via fingerprinting the classification boundary. In Proceedings of the 2021 ACM Asia Conference on Computer and Communications Security. 14\u201325."},{"key":"e_1_3_1_12_2","volume-title":"Proceedings of the 2017 IEEE Symposium on Security and Privacy","author":"Carlini Nicholas","year":"2017","unstructured":"Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In Proceedings of the 2017 IEEE Symposium on Security and Privacy."},{"issue":"1","key":"e_1_3_1_13_2","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10916-023-01925-4","article-title":"Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios","volume":"47","author":"Cascella Marco","year":"2023","unstructured":"Marco Cascella, Jonathan Montomoli, Valentina Bellini, et\u00a0al. 2023. Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios. Journal of Medical Systems 47, 1 (2023), 33.","journal-title":"Journal of Medical Systems"},{"key":"e_1_3_1_14_2","first-page":"13817","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Cha Junbum","year":"2024","unstructured":"Junbum Cha, Wooyoung Kang, Jonghwan Mun, et\u00a0al. 2024. Honeybee: Locality-enhanced projector for multimodal llm. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13817\u201313827."},{"key":"e_1_3_1_15_2","article-title":"Rlhf deciphered: A critical analysis of reinforcement learning from human feedback for llms","author":"Chaudhari Shreyas","year":"2024","unstructured":"Shreyas Chaudhari, Pranjal Aggarwal, Vishvak Murahari, et\u00a0al. 2024. Rlhf deciphered: A critical analysis of reinforcement learning from human feedback for llms. Computing Surveys (2024).","journal-title":"Computing Surveys"},{"key":"e_1_3_1_16_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Chen Dongping","year":"2024","unstructured":"Dongping Chen, Ruoxi Chen, Shilin Zhang, et\u00a0al. 2024. Mllm-as-a-judge: Assessing multimodal llm-as-a-judge with vision-language benchmark. In Proceedings of the 41st International Conference on Machine Learning."},{"issue":"3","key":"e_1_3_1_17_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3572777","article-title":"Perceptual hashing of deep convolutional neural networks for model copy detection","volume":"19","author":"Chen Haozhe","year":"2023","unstructured":"Haozhe Chen, Hang Zhou, Jie Zhang, et\u00a0al. 2023. Perceptual hashing of deep convolutional neural networks for model copy detection. ACM Transactions on Multimedia Computing, Communications and Applications 19, 3 (2023), 1\u201320.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/SP46214.2022.9833747","volume-title":"Proceedings of the 2022 IEEE Symposium on Security and Privacy","author":"Chen Jialuo","year":"2022","unstructured":"Jialuo Chen, Jingyi Wang, Tinglan Peng, et\u00a0al. 2022. Copy, right? a testing framework for copyright protection of deep learning models. In Proceedings of the 2022 IEEE Symposium on Security and Privacy. IEEE, 824\u2013841."},{"key":"e_1_3_1_19_2","unstructured":"Keqin Chen Zhao Zhang Weili Zeng et\u00a0al. 2023. Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic. arXiv:2306.15195. Retrieved from https:\/\/arxiv.org\/abs\/2306.15195"},{"key":"e_1_3_1_20_2","unstructured":"Liang Chen Yatao Bian Yang Deng et\u00a0al. 2023. X-mark: Towards lossless watermarking through lexical redundancy. arXiv:2311.09832. Retrieved from https:\/\/arxiv.org\/abs\/2311.09832"},{"key":"e_1_3_1_21_2","first-page":"6295","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Chen Ruoxin","year":"2022","unstructured":"Ruoxin Chen, Jie Li, Junchi Yan, et\u00a0al. 2022. Input-specific robustness certification for randomized smoothing. In Proceedings of the AAAI Conference on Artificial Intelligence. 6295\u20136303."},{"key":"e_1_3_1_22_2","first-page":"325","volume-title":"Proceedings of the Annual International Cryptology Conference","author":"Christ Miranda","year":"2024","unstructured":"Miranda Christ and Sam Gunn. 2024. Pseudorandom error-correcting codes. In Proceedings of the Annual International Cryptology Conference. Springer, 325\u2013347."},{"key":"e_1_3_1_23_2","first-page":"1125","volume-title":"Proceedings of the 37th Annual Conference on Learning Theory","author":"Christ Miranda","year":"2024","unstructured":"Miranda Christ, Sam Gunn, and Or Zamir. 2024. Undetectable watermarks for language models. In Proceedings of the 37th Annual Conference on Learning Theory. PMLR, 1125\u20131139."},{"key":"e_1_3_1_24_2","unstructured":"Tianyu Cui Yanling Wang Chuanpu Fu et\u00a0al. 2024. Risk taxonomy mitigation and assessment benchmarks of large language model systems. arXiv:2401.05778. Retrieved from https:\/\/arxiv.org\/abs\/2401.05778"},{"key":"e_1_3_1_25_2","article-title":"DriveLLM: Charting the path toward full autonomous driving with large language models","author":"Cui Yaodong","year":"2023","unstructured":"Yaodong Cui, Shucheng Huang, Jiaming Zhong, et\u00a0al. 2023. DriveLLM: Charting the path toward full autonomous driving with large language models. IEEE Transactions on Intelligent Vehicles (2023).","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"issue":"2","key":"e_1_3_1_26_2","first-page":"1","article-title":"From selective deep convolutional features to compact binary representations for image retrieval","volume":"15","author":"Do Thanh-Toan","year":"2019","unstructured":"Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan, et\u00a0al. 2019. From selective deep convolutional features to compact binary representations for image retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications 15, 2 (2019), 1\u201322.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_1_27_2","unstructured":"Danny Driess Fei Xia Mehdi S. M. Sajjadi et\u00a0al. 2023. Palm-e: An embodied multimodal language model. arXiv:2303.03378. Retrieved from https:\/\/arxiv.org\/abs\/2303.03378"},{"key":"e_1_3_1_28_2","unstructured":"Jonathan Evertz Merlin Chlosta Lea Sch\u00f6nherr et\u00a0al. 2024. Whispers in the Machine: Confidentiality in LLM-integrated Systems. arXiv:2402.06922. Retrieved from https:\/\/arxiv.org\/abs\/2402.06922"},{"issue":"4","key":"e_1_3_1_29_2","article-title":"Publicly-detectable watermarking for language models","volume":"1","author":"Fairoze Jaiden","year":"2025","unstructured":"Jaiden Fairoze, Sanjam Garg, Somesh Jha, et\u00a0al. 2025. Publicly-detectable watermarking for language models. IACR Communications in Cryptology 1, 4 (2025).","journal-title":"IACR Communications in Cryptology"},{"key":"e_1_3_1_30_2","first-page":"16091","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Fang Gongfan","year":"2023","unstructured":"Gongfan Fang, Xinyin Ma, Mingli Song, et\u00a0al. 2023. Depgraph: Towards any structural pruning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16091\u201316101."},{"key":"e_1_3_1_31_2","first-page":"1","volume-title":"Proceedings of the 2023 IEEE International Workshop on Information Forensics and Security","author":"Fernandez Pierre","year":"2023","unstructured":"Pierre Fernandez, Antoine Chaffin, Karim Tit, et\u00a0al. 2023. Three bricks to consolidate watermarks for large language models. In Proceedings of the 2023 IEEE International Workshop on Information Forensics and Security. IEEE, 1\u20136."},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1145\/3336191.3371856","volume-title":"Proceedings of the 13th International Conference on Web Search and Data Mining","author":"Feyisetan Oluwaseyi","year":"2020","unstructured":"Oluwaseyi Feyisetan, Borja Balle, Thomas Drake, et\u00a0al. 2020. Privacy-and utility-preserving textual analysis via calibrated multivariate perturbations. In Proceedings of the 13th International Conference on Web Search and Data Mining. 178\u2013186."},{"key":"e_1_3_1_33_2","first-page":"5791","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Fu Jiayi","year":"2024","unstructured":"Jiayi Fu, Xuandong Zhao, Ruihan Yang, et\u00a0al. 2024. GumbelSoft: Diversified language model watermarking via the gumbelmax-trick. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 5791\u20135808."},{"key":"e_1_3_1_34_2","first-page":"311","volume-title":"Proceedings of the European Conference on Information Retrieval","author":"Gab\u00edn Jorge","year":"2025","unstructured":"Jorge Gab\u00edn and Javier Parapar. 2025. Leveraging retrieval-augmented generation for keyphrase synonym suggestion. In Proceedings of the European Conference on Information Retrieval. Springer, 311\u2013327."},{"issue":"2","key":"e_1_3_1_35_2","doi-asserted-by":"crossref","first-page":"2237","DOI":"10.1007\/s11042-022-13314-z","article-title":"A robust technique for biometric image authentication using invisible watermarking","volume":"82","author":"Garg Payal","year":"2023","unstructured":"Payal Garg and Ajit Jain. 2023. A robust technique for biometric image authentication using invisible watermarking. Multimedia Tools and Applications 82, 2 (2023), 2237\u20132253.","journal-title":"Multimedia Tools and Applications"},{"issue":"10","key":"e_1_3_1_36_2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1080\/15265161.2023.2249843","article-title":"Unreliable LLM bioethics assistants: Ethical and pedagogical risks","volume":"23","author":"Goetz Lea","year":"2023","unstructured":"Lea Goetz, Markus Trengove, Artem Trotsyuk, et\u00a0al. 2023. Unreliable LLM bioethics assistants: Ethical and pedagogical risks. The American Journal of Bioethics 23, 10 (2023), 89\u201391.","journal-title":"The American Journal of Bioethics"},{"key":"e_1_3_1_37_2","unstructured":"Ian J. Goodfellow Jonathon Shlens and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv:1412.6572. Retrieved from https:\/\/arxiv.org\/abs\/1412.6572"},{"key":"e_1_3_1_38_2","first-page":"58088","article-title":"Adversarial training for graph neural networks: Pitfalls, solutions, and new directions","volume":"36","author":"Gosch Lukas","year":"2023","unstructured":"Lukas Gosch, Simon Geisler, Daniel Sturm, et\u00a0al. 2023. Adversarial training for graph neural networks: Pitfalls, solutions, and new directions. Advances in Neural Information Processing Systems 36 (2023), 58088\u201358112.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_39_2","unstructured":"Przemyslaw Grabowicz Nicholas Perello and Yair Zick. 2023. Towards an AI Accountability Policy. arXiv:2307.13658. Retrieved from https:\/\/arxiv.org\/abs\/2307.13658"},{"key":"e_1_3_1_40_2","unstructured":"Chenchen Gu Xiang Lisa Li Percy Liang et\u00a0al. 2023. On the learnability of watermarks for language models. arXiv:1409.0473. Retrieved from https:\/\/arxiv.org\/abs\/1701.00133"},{"key":"e_1_3_1_41_2","first-page":"16647","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Gu Xiangming","year":"2024","unstructured":"Xiangming Gu, Xiaosen Zheng, Tianyu Pang, et\u00a0al. 2024. Agent Smith: A single image can jailbreak one million multimodal LLM agents exponentially fast. In Proceedings of the 41st International Conference on Machine Learning. 16647\u201316672."},{"key":"e_1_3_1_42_2","article-title":"Are you stealing my model? sample correlation for fingerprinting deep neural networks","author":"Guan Jiyang","year":"2022","unstructured":"Jiyang Guan, Jian Liang, and Ran He. 2022. Are you stealing my model? sample correlation for fingerprinting deep neural networks. NeurIPS2022(2022).","journal-title":"NeurIPS2022"},{"key":"e_1_3_1_43_2","first-page":"10867","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Guo Jiaxian","year":"2023","unstructured":"Jiaxian Guo, Junnan Li, Dongxu Li, et\u00a0al. 2023. From images to textual prompts: Zero-shot visual question answering with frozen large language models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10867\u201310877."},{"key":"e_1_3_1_44_2","unstructured":"Yucheng Han Chi Zhang Xin Chen et\u00a0al. 2023. Chartllama: A multimodal llm for chart understanding and generation. arXiv:2311.16483. Retrieved from https:\/\/arxiv.org\/abs\/2311.16483"},{"key":"e_1_3_1_45_2","first-page":"1680","volume-title":"Findings of the Association for Computational Linguistics: NAACL 2025","author":"He Pengfei","year":"2025","unstructured":"Pengfei He, Han Xu, Yue Xing, et\u00a0al. 2025. Data poisoning for in-context learning. In Findings of the Association for Computational Linguistics: NAACL 2025. 1680\u20131700."},{"key":"e_1_3_1_46_2","first-page":"1901","volume-title":"Proceedings of the 30th USENIX Security Symposium","author":"He Yingzhe","year":"2021","unstructured":"Yingzhe He, Guozhu Meng, Kai Chen, et\u00a0al. 2021. \\(\\lbrace\\) DRMI \\(\\rbrace\\) : A dataset reduction technology based on mutual information for black-box attacks. In Proceedings of the 30th USENIX Security Symposium. 1901\u20131918."},{"key":"e_1_3_1_47_2","article-title":"Structured pruning for deep convolutional neural networks: A survey","author":"He Yang","year":"2023","unstructured":"Yang He and Lingao Xiao. 2023. Structured pruning for deep convolutional neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_48_2","volume-title":"Proceedings of the ACL.","author":"He Zhiwei","year":"2024","unstructured":"Zhiwei He, Binglin Zhou, Hongkun Hao, et\u00a0al. 2024. Can watermarks survive translation? on the cross-lingual consistency of text watermark for large language models. In Proceedings of the ACL."},{"key":"e_1_3_1_49_2","first-page":"1","volume-title":"Proceedings of the 2012 eCrime Researchers Summit","author":"Helfrich James N.","year":"2012","unstructured":"James N. Helfrich and Rick Neff. 2012. Dual canonicalization: An answer to the homograph attack. In Proceedings of the 2012 eCrime Researchers Summit. IEEE, 1\u201310."},{"key":"e_1_3_1_50_2","first-page":"4067","volume-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","author":"Hou Abe","year":"2024","unstructured":"Abe Hou, Jingyu Zhang, Tianxing He, et\u00a0al. 2024. SemStamp: A semantic watermark with paraphrastic robustness for text generation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 4067\u20134082."},{"issue":"1","key":"e_1_3_1_51_2","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/83.736686","article-title":"Hidden digital watermarks in images","volume":"8","author":"Hsu Chiou-Ting","year":"1999","unstructured":"Chiou-Ting Hsu and Ja-Ling Wu. 1999. Hidden digital watermarks in images. IEEE Transactions on Image Processing 8, 1 (1999), 58\u201368.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_52_2","doi-asserted-by":"crossref","first-page":"117134","DOI":"10.1016\/j.eswa.2022.117134","article-title":"A high-capacity QRD-based blind color image watermarking algorithm incorporated with AI technologies","volume":"199","author":"Hsu Ling-Yuan","year":"2022","unstructured":"Ling-Yuan Hsu, Hwai-Tsu Hu, and Hsien-Hsin Chou. 2022. A high-capacity QRD-based blind color image watermarking algorithm incorporated with AI technologies. Expert Systems with Applications 199 (2022), 117134.","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"e_1_3_1_53_2","first-page":"2568","article-title":"VeriDIP: Verifying ownership of deep neural networks through privacy leakage fingerprints","volume":"21","author":"Hu Aoting","year":"2023","unstructured":"Aoting Hu, Zhigang Lu, Renjie Xie, et\u00a0al. 2023. VeriDIP: Verifying ownership of deep neural networks through privacy leakage fingerprints. IEEE Transactions on Dependable and Secure Computing 21, 4 (2023), 2568\u20132584.","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"e_1_3_1_54_2","first-page":"2256","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Hu Wenbo","year":"2024","unstructured":"Wenbo Hu, Yifan Xu, Yi Li, et\u00a0al. 2024. Bliva: A simple multimodal llm for better handling of text-rich visual questions. In Proceedings of the AAAI Conference on Artificial Intelligence. 2256\u20132264."},{"key":"e_1_3_1_55_2","unstructured":"Zhengmian Hu Lichang Chen Xidong Wu et\u00a0al. 2023. Unbiased watermark for large language models. arXiv:2310.10669. Retrieved from https:\/\/arxiv.org\/abs\/2310.10669"},{"key":"e_1_3_1_56_2","first-page":"5254","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Hu Zhiqiang","year":"2023","unstructured":"Zhiqiang Hu, Lei Wang, Yihuai Lan, et\u00a0al. 2023. LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 5254\u20135276."},{"key":"e_1_3_1_57_2","unstructured":"Baihe Huang Banghua Zhu Hanlin Zhu et\u00a0al. 2023. Towards optimal statistical watermarking. arXiv:2312.07930. Retrieved from https:\/\/arxiv.org\/abs\/2312.07930"},{"key":"e_1_3_1_58_2","first-page":"1039","volume-title":"Proceedings of the 2021 IEEE Symposium on Security and Privacy","author":"Jia Hengrui","year":"2021","unstructured":"Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, et\u00a0al. 2021. Proof-of-learning: Definitions and practice. In Proceedings of the 2021 IEEE Symposium on Security and Privacy. IEEE, 1039\u20131056."},{"key":"e_1_3_1_59_2","first-page":"13388","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Jia Xiaojun","year":"2022","unstructured":"Xiaojun Jia, Yong Zhang, Baoyuan Wu, et\u00a0al. 2022. LAS-AT: Adversarial training with learnable attack strategy. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 13388\u201313398."},{"key":"e_1_3_1_60_2","article-title":"Large AI model empowered multimodal semantic communications","author":"Jiang Feibo","year":"2024","unstructured":"Feibo Jiang, Li Dong, Yubo Peng, et\u00a0al. 2024. Large AI model empowered multimodal semantic communications. IEEE Communications Magazine (2024).","journal-title":"IEEE Communications Magazine"},{"key":"e_1_3_1_61_2","unstructured":"Liming Jiang. 2024. Utilizing Large LanguageModels to Detect Privacy Leaks in Mini-App Code. arXiv:2402.07367. Retrieved from https:\/\/arxiv.org\/abs\/2402.07367"},{"key":"e_1_3_1_62_2","first-page":"3612","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Jiang Zhengyuan","year":"2023","unstructured":"Zhengyuan Jiang, Minghong Fang, and Neil Zhenqiang Gong. 2023. Ipcert: Provably robust intellectual property protection for machine learning. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 3612\u20133621."},{"key":"e_1_3_1_63_2","doi-asserted-by":"crossref","first-page":"4163","DOI":"10.18653\/v1\/2020.findings-emnlp.372","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Jiao Xiaoqi","year":"2020","unstructured":"Xiaoqi Jiao, Yichun Yin, Lifeng Shang, et\u00a0al. 2020. TinyBERT: Distilling BERT for natural language understanding. In Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, 4163\u20134174."},{"key":"e_1_3_1_64_2","first-page":"22185","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Jin Yang","year":"2024","unstructured":"Yang Jin, Zhicheng Sun, Kun Xu, et\u00a0al. 2024. Video-LaVIT: Unified video-language pre-training with decoupled visual-motional tokenization. In Proceedings of the International Conference on Machine Learning. PMLR, 22185\u201322209."},{"key":"e_1_3_1_65_2","first-page":"512","volume-title":"Proceedings of the 2019 IEEE European Symposium on Security and Privacy","author":"Juuti Mika","year":"2019","unstructured":"Mika Juuti, Sebastian Szyller, Samuel Marchal, et\u00a0al. 2019. PRADA: Protecting against DNN model stealing attacks. In Proceedings of the 2019 IEEE European Symposium on Security and Privacy. IEEE, 512\u2013527."},{"issue":"7","key":"e_1_3_1_66_2","doi-asserted-by":"crossref","first-page":"5108","DOI":"10.1109\/TII.2020.3028612","article-title":"DWFCAT: Dual watermarking framework for industrial image authentication and tamper localization","volume":"17","author":"Kamili Asra","year":"2020","unstructured":"Asra Kamili, Nasir N. Hurrah, Shabir A. Parah, et\u00a0al. 2020. DWFCAT: Dual watermarking framework for industrial image authentication and tamper localization. IEEE Transactions on Industrial Informatics 17, 7 (2020), 5108\u20135117.","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"e_1_3_1_67_2","volume-title":"Proceedings of the Socially Responsible Language Modelling Research","author":"Kandpal Nikhil","year":"2023","unstructured":"Nikhil Kandpal, Krishna Pillutla, Alina Oprea, et\u00a0al. 2023. User inference attacks on LLMs. In Proceedings of the Socially Responsible Language Modelling Research."},{"key":"e_1_3_1_68_2","unstructured":"Kaan Efe Kele\u015f \u00d6mer Kaan G\u00fcrb\u00fcz and Mucahid Kutlu. 2023. I know you did not write that! a sampling based watermarking method for identifying machine generated text. arXiv:2311.18054. Retrieved from https:\/\/arxiv.org\/abs\/2311.18054"},{"key":"e_1_3_1_69_2","unstructured":"Jungin Kim Shinwoo Park and Yo-Sub Han. 2025. Marking code without breaking it: Code watermarking for detecting llm-generated code. arXiv:2502.18851. Retrieved from https:\/\/arxiv.org\/abs\/2502.18851"},{"key":"e_1_3_1_70_2","first-page":"17061","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Kirchenbauer John","year":"2023","unstructured":"John Kirchenbauer, Jonas Geiping, Yuxin Wen, et\u00a0al. 2023. A watermark for large language models. In Proceedings of the International Conference on Machine Learning. PMLR, 17061\u201317084."},{"key":"e_1_3_1_71_2","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.23919\/MIPRO57284.2023.10159740","volume-title":"Proceedings of the 2023 46th MIPRO ICT and Electronics Convention","author":"Kitanovski Aleksandar","year":"2023","unstructured":"Aleksandar Kitanovski, Martina Toshevska, and Georgina Mirceva. 2023. Distilbert and roberta models for identification of fake news. In Proceedings of the 2023 46th MIPRO ICT and Electronics Convention. IEEE, 1102\u20131106."},{"key":"e_1_3_1_72_2","article-title":"Generating images with multimodal language models","volume":"36","author":"Koh Jing Yu","year":"2024","unstructured":"Jing Yu Koh, Daniel Fried, and Russ R. Salakhutdinov. 2024. Generating images with multimodal language models. Advances in Neural Information Processing Systems 36 (2024).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_73_2","doi-asserted-by":"crossref","first-page":"2508","DOI":"10.1109\/TIFS.2022.3179945","article-title":"Computational sensor fingerprints","volume":"17","author":"Korus Pawe\u0142","year":"2022","unstructured":"Pawe\u0142 Korus and Nasir Memon. 2022. Computational sensor fingerprints. IEEE Transactions on Information Forensics and Security 17 (2022), 2508\u20132523.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"e_1_3_1_74_2","first-page":"27469","article-title":"Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense","volume":"36","author":"Krishna Kalpesh","year":"2023","unstructured":"Kalpesh Krishna, Yixiao Song, Marzena Karpinska, et\u00a0al. 2023. Paraphrasing evades detectors of ai-generated text, but retrieval is an effective defense. Advances in Neural Information Processing Systems 36 (2023), 27469\u201327500.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_75_2","doi-asserted-by":"crossref","first-page":"5260","DOI":"10.1145\/3637528.3671573","volume-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Kuang Weirui","year":"2024","unstructured":"Weirui Kuang, Bingchen Qian, Zitao Li, et\u00a0al. 2024. Federatedscope-llm: A comprehensive package for fine-tuning large language models in federated learning. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 5260\u20135271."},{"key":"e_1_3_1_76_2","doi-asserted-by":"crossref","first-page":"5260","DOI":"10.1145\/3637528.3671573","volume-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Kuang Weirui","year":"2024","unstructured":"Weirui Kuang, Bingchen Qian, Zitao Li, et\u00a0al. 2024. Federatedscope-llm: A comprehensive package for fine-tuning large language models in federated learning. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 5260\u20135271."},{"key":"e_1_3_1_77_2","unstructured":"Rohith Kuditipudi John Thickstun Tatsunori Hashimoto et\u00a0al. 2023. Robust distortion-free watermarks for language models. arXiv:2307.15593. Retrieved from https:\/\/arxiv.org\/abs\/2307.15593"},{"key":"e_1_3_1_78_2","unstructured":"Ashutosh Kumar Sagarika Singh Shiv Vignesh Murty and Swathy Ragupathy. 2024. The Ethics of Interaction: Mitigating Security Threats in LLMs. arXiv:2401.12273. Retrieved from https:\/\/arxiv.org\/abs\/2401.12273"},{"key":"e_1_3_1_79_2","unstructured":"Zhenzhong Lan Mingda Chen Sebastian Goodman et\u00a0al. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv:1909.11942. Retrieved from https:\/\/arxiv.org\/abs\/1909.11942"},{"key":"e_1_3_1_80_2","first-page":"43","volume-title":"Proceedings of the 2019 IEEE Security and Privacy Workshops","author":"Lee Taesung","year":"2019","unstructured":"Taesung Lee, Benjamin Edwards, Ian Molloy, et\u00a0al. 2019. Defending against neural network model stealing attacks using deceptive perturbations. In Proceedings of the 2019 IEEE Security and Privacy Workshops. IEEE, 43\u201349."},{"key":"e_1_3_1_81_2","first-page":"4890","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Lee Taehyun","year":"2024","unstructured":"Taehyun Lee, Seokhee Hong, Jaewoo Ahn, et\u00a0al. 2024. Who wrote this code? watermarking for code generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 4890\u20134911."},{"key":"e_1_3_1_82_2","unstructured":"Boquan Li Mengdi Zhang Peixin Zhang et\u00a0al. 2024. Resilient watermarking for llm-generated codes. arXiv:2402.07518. Retrieved from https:\/\/arxiv.org\/abs\/2402.07518"},{"key":"e_1_3_1_83_2","first-page":"16250","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Li Jiyao","year":"2023","unstructured":"Jiyao Li and Wei Liu. 2023. Summarization attack via paraphrasing (student abstract). In Proceedings of the AAAI Conference on Artificial Intelligence. 16250\u201316251."},{"key":"e_1_3_1_84_2","first-page":"3368","volume-title":"Findings of the Association for Computational Linguistics","author":"Li Linyang","year":"2023","unstructured":"Linyang Li, Botian Jiang, Pengyu Wang, et\u00a0al. 2023. Watermarking LLMs with weight quantization. In Findings of the Association for Computational Linguistics. 3368\u20133378."},{"key":"e_1_3_1_85_2","unstructured":"Shuai Li Kejiang Chen Kunsheng Tang et\u00a0al. 2023. FunctionMarker: Watermarking language datasets via knowledge injection. arXiv:2311.09535. Retrieved from https:\/\/arxiv.org\/abs\/2311.09535"},{"key":"e_1_3_1_86_2","unstructured":"Sen Li Ruochen Wang Cho-Jui Hsieh et\u00a0al. 2024. Mulan: Multimodal-llm agent for progressive multi-object diffusion. arXiv:2402.12741. Retrieved from https:\/\/arxiv.org\/abs\/2402.12741"},{"key":"e_1_3_1_87_2","unstructured":"Shen Li Liuyi Yao Jinyang Gao et\u00a0al. 2024. Double-I watermark: Protecting model copyright for LLM fine-tuning. arXiv:2402.14883. Retrieved from https:\/\/arxiv.org\/abs\/2402.14883"},{"key":"e_1_3_1_88_2","first-page":"374","volume-title":"Proceedings of the Fourth ACM International Conference on AI in Finance","author":"Li Yinheng","year":"2023","unstructured":"Yinheng Li, Shaofei Wang, Han Ding, et\u00a0al. 2023. Large language models in finance: A survey. In Proceedings of the Fourth ACM International Conference on AI in Finance. 374\u2013382."},{"key":"e_1_3_1_89_2","unstructured":"Yuhang Li Yihan Wang Zhouxing Shi et\u00a0al. 2023. Improving the generation quality of watermarked large language models via word importance scoring. arXiv:2311.09668. Retrieved from https:\/\/arxiv.org\/abs\/2311.09668"},{"key":"e_1_3_1_90_2","first-page":"139","volume-title":"Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis","author":"Li Yuanchun","year":"2021","unstructured":"Yuanchun Li, Ziqi Zhang, Bingyan Liu, et\u00a0al. 2021. ModelDiff: Testing-based DNN similarity comparison for model reuse detection. In Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis. 139\u2013151."},{"key":"e_1_3_1_91_2","unstructured":"Zongjie Li Chaozheng Wang Pingchuan Ma et\u00a0al. 2023. On extracting specialized code abilities from large language models: A feasibility study. arXiv:2303.03012. Retrieved from https:\/\/arxiv.org\/abs\/2303.03012"},{"key":"e_1_3_1_92_2","first-page":"2336","volume-title":"Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security","author":"Li Zongjie","year":"2023","unstructured":"Zongjie Li, Chaozheng Wang, Shuai Wang, et\u00a0al. 2023. Protecting intellectual property of large language model-based code generation apis via watermarks. In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. 2336\u20132350."},{"key":"e_1_3_1_93_2","first-page":"26763","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li Zhang","year":"2024","unstructured":"Zhang Li, Biao Yang, Qiang Liu, et\u00a0al. 2024. Monkey: Image resolution and text label are important things for large multi-modal models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 26763\u201326773."},{"key":"e_1_3_1_94_2","doi-asserted-by":"crossref","first-page":"4426","DOI":"10.1145\/3474085.3475592","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia","author":"Liang Jing","year":"2021","unstructured":"Jing Liang, Li Niu, Fengjun Guo, et\u00a0al. 2021. Visible watermark removal via self-calibrated localization and background refinement. In Proceedings of the 29th ACM International Conference on Multimedia. Association for Computing Machinery, 4426\u20134434."},{"key":"e_1_3_1_95_2","doi-asserted-by":"crossref","unstructured":"Li Lin Neeraj Gupta Yue Zhang et\u00a0al. 2024. Detecting multimedia generated by large ai models: A survey. arXiv:2402.00045. Retrieved from https:\/\/arxiv.org\/abs\/2402.00045","DOI":"10.36227\/techrxiv.170723324.44685515\/v1"},{"key":"e_1_3_1_96_2","first-page":"365","volume-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Lin Xinyu","year":"2024","unstructured":"Xinyu Lin, Wenjie Wang, Yongqi Li, et\u00a0al. 2024. Data-efficient fine-tuning for LLM-based recommendation. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 365\u2013374."},{"key":"e_1_3_1_97_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Liu Aiwei","year":"2023","unstructured":"Aiwei Liu, Leyi Pan, Xuming Hu, et\u00a0al. 2023. A semantic invariant robust watermark for large language models. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_98_2","volume-title":"Proceedings of the ICLR","author":"Liu Aiwei","year":"2024","unstructured":"Aiwei Liu, Leyi Pan, Xuming Hu, et\u00a0al. 2024. An unforgeable publicly verifiable watermark for large language models. In Proceedings of the ICLR."},{"issue":"2","key":"e_1_3_1_99_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3691626","article-title":"A survey of text watermarking in the era of large language models","volume":"57","author":"Liu Aiwei","year":"2024","unstructured":"Aiwei Liu, Leyi Pan, Yijian Lu, et\u00a0al. 2024. A survey of text watermarking in the era of large language models. Comput. Surveys 57, 2 (2024), 1\u201336.","journal-title":"Comput. Surveys"},{"key":"e_1_3_1_100_2","first-page":"30718","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Liu Yepeng","year":"2024","unstructured":"Yepeng Liu and Yuheng Bu. 2024. Adaptive text watermark for large language models. In Proceedings of the 41st International Conference on Machine Learning. 30718\u201330737."},{"key":"e_1_3_1_101_2","unstructured":"Yixin Liu Hongsheng Hu Xun Chen et\u00a0al. 2023. Watermarking Classification Dataset for Copyright Protection. arXiv:2305.13257. Retrieved from https:\/\/arxiv.org\/abs\/2305.13257"},{"key":"e_1_3_1_102_2","unstructured":"Ning Lu Shengcai Liu Rui He et\u00a0al. 2023. Large language models can be guided to evade AI-generated text detection. arXiv:2305.10847. Retrieved from https:\/\/arxiv.org\/abs\/2305.10847"},{"key":"e_1_3_1_103_2","unstructured":"Nils Lukas Yuxuan Zhang and Florian Kerschbaum. 2019. Deep neural network fingerprinting by conferrable adversarial examples. arXiv:1912.00888. Retrieved from https:\/\/arxiv.org\/abs\/1912.00888"},{"key":"e_1_3_1_104_2","unstructured":"Aleksander Madry Aleksandar Makelov Ludwig Schmidt et\u00a0al. 2017. Towards deep learning models resistant to adversarial attacks. arXiv:1706.06083. Retrieved from https:\/\/arxiv.org\/abs\/1706.06083"},{"key":"e_1_3_1_105_2","first-page":"227","volume-title":"Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)","author":"Merkhofer Elizabeth M.","year":"2022","unstructured":"Elizabeth M. Merkhofer, John Henderson, Abigail S. Gertner, et\u00a0al. 2022. Practical attacks on machine translation using paraphrase. In Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track). 227\u2013239."},{"issue":"5","key":"e_1_3_1_106_2","doi-asserted-by":"crossref","first-page":"750","DOI":"10.3390\/sym13050750","article-title":"Fingerprint classification based on deep learning approaches: experimental findings and comparisons","volume":"13","author":"Militello Carmelo","year":"2021","unstructured":"Carmelo Militello, Leonardo Rundo, Salvatore Vitabile, et\u00a0al. 2021. Fingerprint classification based on deep learning approaches: experimental findings and comparisons. Symmetry 13, 5 (2021), 750.","journal-title":"Symmetry"},{"key":"e_1_3_1_107_2","first-page":"2574","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Moosavi-Dezfooli Seyed-Mohsen","year":"2016","unstructured":"Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, and Pascal Frossard. 2016. Deepfool: A simple and accurate method to fool deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2574\u20132582."},{"key":"e_1_3_1_108_2","unstructured":"Stephen Moskal Sam Laney Erik Hemberg et\u00a0al. 2023. LLMs Killed the Script Kiddie: How Agents Supported by Large Language Models Change the Landscape of Network Threat Testing. arXiv:2310.06936. Retrieved from https:\/\/arxiv.org\/abs\/2310.06936"},{"key":"e_1_3_1_109_2","volume-title":"Proceedings of the Multi-Agent Security Workshop@ NeurIPS\u201923","author":"Motwani Sumeet Ramesh","year":"2023","unstructured":"Sumeet Ramesh Motwani, Mikhail Baranchuk, Lewis Hammond, et\u00a0al. 2023. A perfect collusion benchmark: How can AI agents be prevented from colluding with information-theoretic undetectability?. In Proceedings of the Multi-Agent Security Workshop@ NeurIPS\u201923."},{"key":"e_1_3_1_110_2","unstructured":"Travis Munyer and Xin Zhong. 2023. Deeptextmark: Deep learning based text watermarking for detection of large language model generated text. arXiv:2305.05773. Retrieved from https:\/\/arxiv.org\/abs\/2305.05773"},{"key":"e_1_3_1_111_2","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1145\/3600211.3604754","volume-title":"Proceedings of the 2023 AAAI\/ACM Conference on AI, Ethics, and Society","author":"Venkit Pranav Narayanan","year":"2023","unstructured":"Pranav Narayanan Venkit. 2023. Towards a holistic approach: Understanding sociodemographic biases in NLP models using an interdisciplinary lens. In Proceedings of the 2023 AAAI\/ACM Conference on AI, Ethics, and Society. 1004\u20131005."},{"key":"e_1_3_1_112_2","unstructured":"Leyi Pan Aiwei Liu Shiyu Huang et\u00a0al. 2025. Can LLM watermarks robustly prevent unauthorized knowledge distillation? arXiv:2502.11598. Retrieved from https:\/\/arxiv.org\/abs\/2502.11598"},{"key":"e_1_3_1_113_2","first-page":"1327","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Pan Xudong","year":"2022","unstructured":"Xudong Pan, Yifan Yan, Mi Zhang, et\u00a0al. 2022. Metav: A meta-verifier approach to task-agnostic model fingerprinting. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1327\u20131336."},{"key":"e_1_3_1_114_2","unstructured":"Qi Pang Shengyuan Hu Wenting Zheng et\u00a0al. 2024. Attacking LLM Watermarks by Exploiting Their Strengths. arXiv:2402.16187. Retrieved from https:\/\/arxiv.org\/abs\/2402.16187"},{"key":"e_1_3_1_115_2","first-page":"79155","article-title":"The refinedweb dataset for falcon llm: Outperforming curated corpora with web data only","volume":"36","author":"Penedo Guilherme","year":"2023","unstructured":"Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Hamza Alobeidli, Alessandro Cappelli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The refinedweb dataset for falcon llm: Outperforming curated corpora with web data only. Advances in Neural Information Processing Systems 36 (2023), 79155\u201379172.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_116_2","doi-asserted-by":"crossref","first-page":"7653","DOI":"10.18653\/v1\/2023.acl-long.423","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Peng Wenjun","year":"2023","unstructured":"Wenjun Peng, Jingwei Yi, Fangzhao Wu, et\u00a0al. 2023. Are you copying my model? protecting the copyright of large language models for EaaS via backdoor watermark. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 7653\u20137668."},{"key":"e_1_3_1_117_2","first-page":"13430","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Peng Zirui","year":"2022","unstructured":"Zirui Peng, Shaofeng Li, Guoxing Chen, et\u00a0al. 2022. Fingerprinting deep neural networks globally via universal adversarial perturbations. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13430\u201313439."},{"issue":"2","key":"e_1_3_1_118_2","first-page":"18","article-title":"Near-duplicate sequence search at scale for large language model memorization evaluation","volume":"1","author":"Peng Zhencan","year":"2023","unstructured":"Zhencan Peng, Zhizhi Wang, and Dong Deng. 2023. Near-duplicate sequence search at scale for large language model memorization evaluation. Proc. ACM Manag. Data 1, 2(2023), 18 pages.","journal-title":"Proc. ACM Manag. Data"},{"key":"e_1_3_1_119_2","doi-asserted-by":"crossref","first-page":"103859","DOI":"10.1016\/j.artint.2023.103859","article-title":"Natural language watermarking via paraphraser-based lexical substitution","volume":"317","author":"Qiang Jipeng","year":"2023","unstructured":"Jipeng Qiang, Shiyu Zhu, Yun Li, et\u00a0al. 2023. Natural language watermarking via paraphraser-based lexical substitution. Artificial Intelligence 317 (2023), 103859.","journal-title":"Artificial Intelligence"},{"key":"e_1_3_1_120_2","unstructured":"Wenjie Qu Dong Yin Zixin He et\u00a0al. 2024. Provably robust multi-bit watermarking for AI-generated text via error correction code. arXiv:2401.16820. Retrieved from https:\/\/arxiv.org\/abs\/2401.16820"},{"key":"e_1_3_1_121_2","doi-asserted-by":"crossref","first-page":"7499","DOI":"10.18653\/v1\/2024.emnlp-main.427","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Raina Vyas","year":"2024","unstructured":"Vyas Raina, Adian Liusie, and Mark Gales. 2024. Is LLM-as-a-judge robust? investigating universal adversarial attacks on zero-shot LLM assessment. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 7499\u20137517."},{"key":"e_1_3_1_122_2","first-page":"14501","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"35","author":"Ramp\u00e1\u0161ek Ladislav","year":"2022","unstructured":"Ladislav Ramp\u00e1\u0161ek, Michael Galkin, Vijay Prakash Dwivedi, et\u00a0al. 2022. Recipe for a general, powerful, scalable graph transformer. In Proceedings of the Advances in Neural Information Processing Systems. S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35, Curran Associates, Inc., 14501\u201314515."},{"issue":"1","key":"e_1_3_1_123_2","article-title":"The six emotional dimension (6DE) model: A multidimensional approach to analyzing human emotions and unlocking the potential of emotionally intelligent artificial intelligence (AI) via large language models (LLM)","volume":"1","author":"Ratican Jay","year":"2023","unstructured":"Jay Ratican and James Hutson. 2023. The six emotional dimension (6DE) model: A multidimensional approach to analyzing human emotions and unlocking the potential of emotionally intelligent artificial intelligence (AI) via large language models (LLM). Journal of Artificial Intelligence and Robotics 1, 1 (2023).","journal-title":"Journal of Artificial Intelligence and Robotics"},{"key":"e_1_3_1_124_2","first-page":"2837","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Reichman Benjamin","year":"2023","unstructured":"Benjamin Reichman and Larry Heck. 2023. Cross-modal dense passage retrieval for outside knowledge visual question answering. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2837\u20132842."},{"key":"e_1_3_1_125_2","unstructured":"Huali Ren Anli Yan Xiaojun Ren et\u00a0al. 2023. Ganfinger: Gan-based fingerprint generation for deep neural network ownership verification. arXiv:2312.15617. Retrieved from https:\/\/arxiv.org\/abs\/2312.15617"},{"key":"e_1_3_1_126_2","unstructured":"Jie Ren Han Xu Pengfei He et\u00a0al. 2024. Copyright protection in generative AI: A technical perspective. arXiv:2402.02333. Retrieved from https:\/\/arxiv.org\/abs\/2402.02333"},{"key":"e_1_3_1_127_2","doi-asserted-by":"crossref","first-page":"613","DOI":"10.18653\/v1\/2024.findings-naacl.40","volume-title":"Findings of the Association for Computational Linguistics: NAACL 2024","author":"Ren Jie","year":"2024","unstructured":"Jie Ren, Han Xu, Yiding Liu, et\u00a0al. 2024. A robust semantics-based watermark for large language model against paraphrasing. In Findings of the Association for Computational Linguistics: NAACL 2024. 613\u2013625."},{"key":"e_1_3_1_128_2","first-page":"554","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Roberts Jonathan","year":"2024","unstructured":"Jonathan Roberts, Timo L\u00fcddecke, Rehan Sheikh, et\u00a0al. 2024. Charting new territories: Exploring the geographic and geospatial capabilities of multimodal llms. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 554\u2013563."},{"key":"e_1_3_1_129_2","unstructured":"Vinu Sankar Sadasivan Aounon Kumar Sriram Balasubramanian et\u00a0al. 2023. Can ai-generated text be reliably detected? arXiv:2303.11156. Retrieved from https:\/\/arxiv.org\/abs\/2303.11156"},{"key":"e_1_3_1_130_2","first-page":"5563","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Sahin Ugur","year":"2024","unstructured":"Ugur Sahin, Hang Li, Qadeer Khan, et\u00a0al. 2024. Enhancing multimodal compositional reasoning of visual language models with generative negative mining. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 5563\u20135573."},{"issue":"5","key":"e_1_3_1_131_2","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","article-title":"Term-weighting approaches in automatic text retrieval","volume":"24","author":"Salton Gerard","year":"1988","unstructured":"Gerard Salton and Chris Buckley. 1988. Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24, 5 (1988), 513\u2013523.","journal-title":"Inf. Process. Manag."},{"issue":"2","key":"e_1_3_1_132_2","doi-asserted-by":"crossref","first-page":"1048","DOI":"10.1109\/COMST.2021.3064259","article-title":"A survey on device behavior fingerprinting: Data sources, techniques, application scenarios, and datasets","volume":"23","author":"S\u00e1nchez Pedro Miguel S\u00e1nchez","year":"2021","unstructured":"Pedro Miguel S\u00e1nchez S\u00e1nchez, Jose Maria Jorquera Valero, Alberto Huertas Celdr\u00e1n, et\u00a0al. 2021. A survey on device behavior fingerprinting: Data sources, techniques, application scenarios, and datasets. IEEE Communications Surveys and Tutorials 23, 2 (2021), 1048\u20131077.","journal-title":"IEEE Communications Surveys and Tutorials"},{"key":"e_1_3_1_133_2","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond et\u00a0al. 2019. DistilBERT a distilled version of BERT: Smaller faster cheaper and lighter. arXiv:1910.01108. Retrieved from https:\/\/arxiv.org\/abs\/1910.01108"},{"key":"e_1_3_1_134_2","first-page":"15263","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sanyal Sunandini","year":"2022","unstructured":"Sunandini Sanyal, Sravanti Addepalli, and R. Venkatesh Babu. 2022. Towards data-free model stealing in a hard label setting. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 15263\u201315272."},{"key":"e_1_3_1_135_2","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1145\/3618257.3624845","volume-title":"Proceedings of the 2023 ACM on Internet Measurement Conference","author":"Sarabi Armin","year":"2023","unstructured":"Armin Sarabi, Tongxin Yin, and Mingyan Liu. 2023. An llm-based framework for fingerprinting internet-connected devices. In Proceedings of the 2023 ACM on Internet Measurement Conference. 478\u2013484."},{"key":"e_1_3_1_136_2","unstructured":"Ryoma Sato Yuki Takezawa Han Bao et\u00a0al. 2023. Embarrassingly simple text watermarks. arXiv:2310.08920. Retrieved from https:\/\/arxiv.org\/abs\/2310.08920"},{"key":"e_1_3_1_137_2","unstructured":"Ryoma Sato Yuki Takezawa Han Bao Kenta Niwa and Makoto Yamada. 2023. Embarrassingly simple text watermarks. arXiv:2310.08920. Retrieved from https:\/\/arxiv.org\/abs\/2310.08920"},{"key":"e_1_3_1_138_2","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1145\/3437880.3460401","volume-title":"Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security","author":"Shafieinejad Masoumeh","year":"2021","unstructured":"Masoumeh Shafieinejad, Nils Lukas, Jiaqi Wang, Xinda Li, and Florian Kerschbaum. 2021. On the robustness of backdoor-based watermarking in deep neural networks. In Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia Security. 177\u2013188."},{"key":"e_1_3_1_139_2","first-page":"464","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)","author":"Shaw Peter","year":"2018","unstructured":"Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. 2018. Self-attention with relative position representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). Association for Computational Linguistics, 464\u2013468."},{"key":"e_1_3_1_140_2","unstructured":"Xicong Shen Yang Liu Huiqi Liu et\u00a0al. 2023. A split-and-privatize framework for large language model fine-tuning. arXiv:2312.15603. Retrieved from https:\/\/arxiv.org\/abs\/2312.15603"},{"key":"e_1_3_1_141_2","first-page":"9547","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research)","author":"Shi Han","year":"2021","unstructured":"Han Shi, Jiahui Gao, Xiaozhe Ren, et\u00a0al. 2021. SparseBERT: Rethinking the importance analysis in self-attention. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research).Marina Meila and Tong Zhang (Eds.), PMLR, 9547\u20139557."},{"key":"e_1_3_1_142_2","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1162\/tacl_a_00639","article-title":"Red teaming language model detectors with language models","volume":"12","author":"Shi Zhouxing","year":"2024","unstructured":"Zhouxing Shi, Yihan Wang, Fan Yin, et\u00a0al. 2024. Red teaming language model detectors with language models. Transactions of the Association for Computational Linguistics 12 (2024), 174\u2013189.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"e_1_3_1_143_2","unstructured":"Karanpartap Singh and James Zou. 2023. New evaluation metrics capture quality degradation due to LLM watermarking. arXiv:2312.02382. Retrieved from https:\/\/arxiv.org\/abs\/2312.02382"},{"key":"e_1_3_1_144_2","first-page":"13931","article-title":"Revisiting adversarial training for imagenet: Architectures, training and generalization across threat models","volume":"36","author":"Singh Naman Deep","year":"2023","unstructured":"Naman Deep Singh, Francesco Croce, and Matthias Hein. 2023. Revisiting adversarial training for imagenet: Architectures, training and generalization across threat models. Advances in Neural Information Processing Systems 36 (2023), 13931\u201313955.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_145_2","first-page":"5176","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Sun Jiao","year":"2021","unstructured":"Jiao Sun, Xuezhe Ma, and Nanyun Peng. 2021. AESOP: Paraphrase generation with adaptive syntactic control. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 5176\u20135189."},{"key":"e_1_3_1_146_2","first-page":"2411","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Sun Ruizhou","year":"2023","unstructured":"Ruizhou Sun, Yukun Su, and Qingyao Wu. 2023. Denet: Disentangled embedding network for visible watermark removal. In Proceedings of the AAAI Conference on Artificial Intelligence. 2411\u20132419."},{"key":"e_1_3_1_147_2","first-page":"5257","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Sun Xiaofei","year":"2023","unstructured":"Xiaofei Sun, Xiaoya Li, Yuxian Meng, et\u00a0al. 2023. Defending against backdoor attacks in natural language generation. In Proceedings of the AAAI Conference on Artificial Intelligence. 5257\u20135265."},{"key":"e_1_3_1_148_2","first-page":"652","volume-title":"Proceedings of the ACM Web Conference 2022","author":"Sun Zhensu","year":"2022","unstructured":"Zhensu Sun, Xiaoning Du, Fu Song, et\u00a0al. 2022. Coprotector: Protect open-source code against unauthorized training usage with data poisoning. In Proceedings of the ACM Web Conference 2022. 652\u2013660."},{"key":"e_1_3_1_149_2","first-page":"1561","volume-title":"Association for Computing Machinery.","author":"Sun Zhensu","year":"2023","unstructured":"Zhensu Sun, Xiaoning Du, Fu Song, et\u00a0al. 2023. CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models. In Association for Computing Machinery.1561\u20131572."},{"key":"e_1_3_1_150_2","first-page":"1561","volume-title":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","author":"Sun Zhensu","year":"2023","unstructured":"Zhensu Sun, Xiaoning Du, Fu Song, and Li Li. 2023. Codemark: Imperceptible watermarking for code datasets against neural code completion models. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1561\u20131572."},{"key":"e_1_3_1_151_2","article-title":"Necessary and sufficient watermark for large language models","author":"Takezawa Yuki","year":"2023","unstructured":"Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, and Makoto Yamada. 2023. Necessary and sufficient watermark for large language models. Transactions on Machine Learning Research (2023).","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_3_1_152_2","unstructured":"Leonard Tang Gavin Uberti and Tom Shlomi. 2023. Baselines for identifying watermarked large language models. arXiv:2305.18456. Retrieved from https:\/\/arxiv.org\/abs\/2305.18456"},{"issue":"1","key":"e_1_3_1_153_2","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1145\/3606274.3606279","article-title":"Did you train on my dataset? towards public dataset protection with cleanlabel backdoor watermarking","volume":"25","author":"Tang Ruixiang","year":"2023","unstructured":"Ruixiang Tang, Qizhang Feng, Ninghao Liu, et\u00a0al. 2023. Did you train on my dataset? towards public dataset protection with cleanlabel backdoor watermarking. ACM SIGKDD Explorations Newsletter 25, 1 (2023), 43\u201353.","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"e_1_3_1_154_2","first-page":"2327","volume-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Tang Raphael","year":"2024","unstructured":"Raphael Tang, Crystina Zhang, Xueguang Ma, et\u00a0al. 2024. Found in the middle: Permutation self-consistency improves listwise ranking in large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2327\u20132340."},{"key":"e_1_3_1_155_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone et\u00a0al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"issue":"1","key":"e_1_3_1_156_2","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/TAI.2021.3068322","article-title":"SemanticHash: Hash coding via semantics-guided label prototype learning","volume":"2","author":"Tu Cheng-Hao","year":"2021","unstructured":"Cheng-Hao Tu, Huei-Fang Yang, Shih-Min Yang, et\u00a0al. 2021. SemanticHash: Hash coding via semantics-guided label prototype learning. IEEE Transactions on Artificial Intelligence 2, 1 (2021), 42\u201357.","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"e_1_3_1_157_2","doi-asserted-by":"crossref","first-page":"109393","DOI":"10.1016\/j.comnet.2022.109393","article-title":"MAC address de-randomization for WiFi device counting: Combining temporal-and content-based fingerprints","volume":"218","author":"Uras Marco","year":"2022","unstructured":"Marco Uras, Enrico Ferrara, Raimondo Cossu, et\u00a0al. 2022. MAC address de-randomization for WiFi device counting: Combining temporal-and content-based fingerprints. Computer Networks 218 (2022), 109393.","journal-title":"Computer Networks"},{"key":"e_1_3_1_158_2","first-page":"12894","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Vaswani Ashish","year":"2021","unstructured":"Ashish Vaswani, Prajit Ramachandran, Aravind Srinivas, et\u00a0al. 2021. Scaling local self-attention for parameter efficient visual backbones. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12894\u201312904."},{"key":"e_1_3_1_159_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, et\u00a0al. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems. Curran Associates, Inc."},{"key":"e_1_3_1_160_2","unstructured":"Gaurav Verma Minje Choi Kartik Sharma et\u00a0al. 2024. Mysterious projections: Multimodal LLMs gain domain-specific visual capabilities without richer cross-modal projections. arXiv:2402.16832. Retrieved from https:\/\/arxiv.org\/abs\/2402.16832"},{"key":"e_1_3_1_161_2","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1145\/3643762","article-title":"Core: Resolving code quality issues using llms","volume":"1","author":"Wadhwa Nalin","year":"2024","unstructured":"Nalin Wadhwa, Jui Pradhan, Atharv Sonwane, et\u00a0al. 2024. Core: Resolving code quality issues using llms. Proceedings of the ACM on Software Engineering 1, FSE (2024), 789\u2013811.","journal-title":"Proceedings of the ACM on Software Engineering"},{"key":"e_1_3_1_162_2","unstructured":"Jingtan Wang Xinyang Lu Zitong Zhao et\u00a0al. 2023. WASA: Watermark-based source attribution for large language model-generated data. arXiv:2310.00646. Retrieved from https:\/\/arxiv.org\/abs\/2310.00646"},{"key":"e_1_3_1_163_2","unstructured":"Lean Wang Wenkai Yang Deli Chen et\u00a0al. 2023. Towards codable text watermarking for large language models. arXiv:2307.15992. Retrieved from https:\/\/arxiv.org\/abs\/2307.15992"},{"key":"e_1_3_1_164_2","doi-asserted-by":"crossref","first-page":"1808","DOI":"10.1145\/3503161.3548390","volume-title":"Proceedings of the 30th ACM International Conference on Multimedia","author":"Wang Run","year":"2022","unstructured":"Run Wang, Haoxuan Li, Lingzhou Mu, et\u00a0al. 2022. Rethinking the vulnerability of dnn watermarking: Are watermarks robust against naturalness-aware perturbations?. In Proceedings of the 30th ACM International Conference on Multimedia. 1808\u20131818."},{"key":"e_1_3_1_165_2","first-page":"1","volume-title":"Proceedings of the 2021 IEEE International Symposium on Circuits and Systems","author":"Wang Si","year":"2021","unstructured":"Si Wang and Chip-Hong Chang. 2021. Fingerprinting deep neural networks-a deepfool approach. In Proceedings of the 2021 IEEE International Symposium on Circuits and Systems. IEEE, 1\u20135."},{"key":"e_1_3_1_166_2","first-page":"11998","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang Tan","year":"2023","unstructured":"Tan Wang, Kevin Lin, Linjie Li, et\u00a0al. 2023. Equivariant similarity for vision-language foundation models. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 11998\u201312008."},{"key":"e_1_3_1_167_2","unstructured":"Yi Wang Yinan He Yizhuo Li et\u00a0al. 2023. Internvid: A large-scale video-text dataset for multimodal understanding and generation. arXiv:2307.06942. Retrieved from https:\/\/arxiv.org\/abs\/2307.06942"},{"key":"e_1_3_1_168_2","first-page":"12273","volume-title":"Proceedings of the 34th AAAI Conference on Artificial Intelligence","author":"Wang Yulong","year":"2020","unstructured":"Yulong Wang, Xiaolu Zhang, Lingxi Xie, et\u00a0al. 2020. Pruning from Scratch. In Proceedings of the 34th AAAI Conference on Artificial Intelligence. AAAI Press, 12273\u201312280."},{"issue":"4","key":"e_1_3_1_169_2","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C. Bovik, Hamid R. Sheikh, et\u00a0al. 2004. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing 13, 4 (2004), 600\u2013612.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_170_2","first-page":"1648","volume-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Wang Zezhong","year":"2024","unstructured":"Zezhong Wang, Fangkai Yang, Lu Wang, et\u00a0al. 2024. SELF-GUARD: Empower the LLM to safeguard itself. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1648\u20131668."},{"key":"e_1_3_1_171_2","unstructured":"Johnny Tian-Zheng Wei Ryan Yixiang Wang and Robin Jia. 2024. Proving membership in LLM pretraining data via data watermarks. arXiv:2402.10892. Retrieved from https:\/\/arxiv.org\/abs\/2402.10892"},{"key":"e_1_3_1_172_2","first-page":"38","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, et\u00a0al. 2020. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.Qun Liu and David Schlangen (Eds.), Association for Computational Linguistics, Online, 38\u201345."},{"key":"e_1_3_1_173_2","first-page":"53251","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Wouters Bram","year":"2024","unstructured":"Bram Wouters. 2024. Optimizing watermarks for large language models. In Proceedings of the 41st International Conference on Machine Learning. 53251\u201353269."},{"key":"e_1_3_1_174_2","unstructured":"Bingyang Wu Yinmin Zhong Zili Zhang et\u00a0al. 2023. Fast Distributed Inference Serving for Large Language Models. arXiv:2305.05920. Retrieved from https:\/\/arxiv.org\/abs\/2305.05920"},{"key":"e_1_3_1_175_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, et\u00a0al. 2024. Next-gpt: Any-to-any multimodal llm. In Proceedings of the 41st International Conference on Machine Learning."},{"key":"e_1_3_1_176_2","unstructured":"Yihan Wu Zhengmian Hu Hongyang Zhang et\u00a0al. 2023. Dipmark: A stealthy efficient and resilient watermark for large language models. arXiv:2310.07710. Retrieved from https:\/\/arxiv.org\/abs\/2310.07710"},{"key":"e_1_3_1_177_2","first-page":"389","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Xia Bin","year":"2024","unstructured":"Bin Xia, Shiyin Wang, Yingfan Tao, et\u00a0al. 2024. Llmga: Multimodal large language model based generation assistant. In Proceedings of the European Conference on Computer Vision. Springer, 389\u2013406."},{"key":"e_1_3_1_178_2","first-page":"3277","volume-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","author":"Xu Jiashu","year":"2024","unstructured":"Jiashu Xu, Fei Wang, Mingyu Ma, et\u00a0al. 2024. Instructional fingerprinting of large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 3277\u20133306."},{"key":"e_1_3_1_179_2","unstructured":"Mengwei Xu Wangsong Yin Dongqi Cai et\u00a0al. 2024. A Survey of Resource-efficient LLM and Multimodal Foundation Models. arXiv:2401.08092. Retrieved from https:\/\/arxiv.org\/abs\/2401.08092"},{"key":"e_1_3_1_180_2","unstructured":"Weilin Xu David Evans and Yanjun Qi. 2017. Feature squeezing: Detecting adversarial examples in deep neural networks. arXiv:1704.01155. Retrieved from https:\/\/arxiv.org\/abs\/1704.01155"},{"key":"e_1_3_1_181_2","first-page":"59304","article-title":"To repeat or not to repeat: Insights from scaling llm under token-crisis","volume":"36","author":"Xue Fuzhao","year":"2023","unstructured":"Fuzhao Xue, Yao Fu, Wangchunshu Zhou, et\u00a0al. 2023. To repeat or not to repeat: Insights from scaling llm under token-crisis. Advances in Neural Information Processing Systems 36 (2023), 59304\u201359322.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_182_2","unstructured":"Mingfu Xue Xin Wang Yinghao Wu et\u00a0al. 2022. InFIP: An explainable DNN intellectual property protection method based on intrinsic features. arXiv:2210.07481. Retrieved from https:\/\/arxiv.org\/abs\/2210.07481"},{"key":"e_1_3_1_183_2","doi-asserted-by":"crossref","first-page":"2569","DOI":"10.1145\/3626772.3657959","volume-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Yadav Vikas","year":"2024","unstructured":"Vikas Yadav, Zheng Tang, and Vijay Srinivasan. 2024. Pag-llm: Paraphrase and aggregate with large language models for minimizing intent classification errors. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2569\u20132573."},{"key":"e_1_3_1_184_2","unstructured":"Borui Yang Wei Li Liyao Xiang et\u00a0al. 2023. Towards code watermarking with dual-channel transformations. arXiv:2309.00860. Retrieved from https:\/\/arxiv.org\/abs\/2309.00860"},{"key":"e_1_3_1_185_2","volume-title":"Proceedings of the 31st International Joint Conference on Artificial Intelligence","author":"Yang Kang","year":"2022","unstructured":"Kang Yang, Run Wang, and Lina Wang. 2022. Metafinger: Fingerprinting the deep neural networks with meta-training. In Proceedings of the 31st International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_1_186_2","volume-title":"Proceedings of the ICLR","author":"Yang Xianjun","year":"2024","unstructured":"Xianjun Yang, Wei Cheng, Yue Wu, et\u00a0al. 2024. DNA-GPT: Divergent N-Gram analysis for training-free detection of GPT-generated text. In Proceedings of the ICLR."},{"key":"e_1_3_1_187_2","unstructured":"Xinyu Yang and Jizhe Zhou. 2024. Research about the Ability of LLM in the Tamper-Detection Area. arXiv:2401.13504. Retrieved from https:\/\/arxiv.org\/abs\/2401.13504"},{"key":"e_1_3_1_188_2","volume-title":"Proceedings of the ICLR 2024 Workshop on Secure and Trustworthy Large Language Models","author":"Ye Xiaoyu","unstructured":"Xiaoyu Ye, Hao Huang, Jiaqi An, et\u00a0al. [n.d.]. DUAW: Data-free universal adversarial watermark against stable diffusion customization. In Proceedings of the ICLR 2024 Workshop on Secure and Trustworthy Large Language Models."},{"key":"e_1_3_1_189_2","first-page":"9474","article-title":"Lofit: Localized fine-tuning on llm representations","volume":"37","author":"Yin Fangcong","year":"2024","unstructured":"Fangcong Yin, Xi Ye, and Greg Durrett. 2024. Lofit: Localized fine-tuning on llm representations. Advances in Neural Information Processing Systems 37 (2024), 9474\u20139506.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_190_2","first-page":"26650","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Yin Zhenfei","year":"2023","unstructured":"Zhenfei Yin, Jiong Wang, Jianjian Cao, Zhelun Shi, Dingning Liu, Mukai Li, Xiaoshui Huang, Zhiyong Wang, Lu Sheng, Lei Bai, et\u00a0al. 2023. LAMM: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 26650\u201326685."},{"key":"e_1_3_1_191_2","first-page":"2092","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Yoo KiYoon","year":"2023","unstructured":"KiYoon Yoo, Wonhyuk Ahn, Jiho Jang, et\u00a0al. 2023. Robust multi-bit natural language watermarking through invariant features. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Toronto, Canada, 2092\u20132115."},{"key":"e_1_3_1_192_2","first-page":"14448","volume-title":"Proceedings of the IEEE\/CVF International conference on computer vision","author":"Yu Ning","year":"2021","unstructured":"Ning Yu, Vladislav Skripniuk, Sahar Abdelnabi, et\u00a0al. 2021. Artificial fingerprinting for generative models: Rooting deepfake attribution in training data. In Proceedings of the IEEE\/CVF International conference on computer vision. 14448\u201314457."},{"key":"e_1_3_1_193_2","first-page":"1467","volume-title":"Findings of the Association for Computational Linguistics","author":"Yuan Tongxin","year":"2024","unstructured":"Tongxin Yuan, Zhiwei He, Lingzhong Dong, et\u00a0al. 2024. R-Judge: Benchmarking safety risk awareness for LLM agents. In Findings of the Association for Computational Linguistics. 1467\u20131490."},{"key":"e_1_3_1_194_2","first-page":"44","volume-title":"Proceedings of the 15th ACM Conference on Recommender Systems","author":"Yue Zhenrui","year":"2021","unstructured":"Zhenrui Yue, Zhankui He, Huimin Zeng, et\u00a0al. 2021. Black-box attacks on sequential recommenders via data-free model extraction. In Proceedings of the 15th ACM Conference on Recommender Systems. 44\u201354."},{"key":"e_1_3_1_195_2","unstructured":"Or Zamir. 2024. Excuse me sir? Your language model is leaking (information). arXiv:2401.10360. Retrieved from https:\/\/arxiv.org\/abs\/2401.10360"},{"key":"e_1_3_1_196_2","first-page":"126332","article-title":"Huref: Human-readable fingerprint for large language models","volume":"37","author":"Zeng Boyi","year":"2024","unstructured":"Boyi Zeng, Lizheng Wang, Yuncong Hu, et\u00a0al. 2024. Huref: Human-readable fingerprint for large language models. Advances in Neural Information Processing Systems 37 (2024), 126332\u2013126362.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_197_2","doi-asserted-by":"crossref","first-page":"9637","DOI":"10.18653\/v1\/2024.acl-long.521","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhan Jun","year":"2024","unstructured":"Jun Zhan, Junqi Dai, Jiasheng Ye, et\u00a0al. 2024. AnyGPT: Unified multimodal LLM with discrete sequence modeling. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 9637\u20139662."},{"key":"e_1_3_1_198_2","volume-title":"Proceedings of the ICLR 2024 Workshop on Secure and Trustworthy Large Language Models","author":"Zhang Hanlin","year":"2024","unstructured":"Hanlin Zhang, Benjamin L. Edelman, Danilo Francati, Daniele Venturi, Giuseppe Ateniese, and Boaz Barak. 2024. Watermarks in the sand: Impossibility of strong watermarking for generative models. In Proceedings of the ICLR 2024 Workshop on Secure and Trustworthy Large Language Models."},{"issue":"8","key":"e_1_3_1_199_2","first-page":"4005","article-title":"Deep model intellectual property protection via deep watermarking","volume":"44","author":"Zhang Jie","year":"2021","unstructured":"Jie Zhang, Dongdong Chen, Jing Liao, et\u00a0al. 2021. Deep model intellectual property protection via deep watermarking. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 8 (2021), 4005\u20134020.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_200_2","first-page":"1813","volume-title":"Proceedings of the 33rd USENIX Security Symposium","author":"Zhang Ruisi","year":"2024","unstructured":"Ruisi Zhang, Shehzeen Samarah Hussain, Paarth Neekhara, et\u00a0al. 2024. \\(\\lbrace\\) REMARK-LLM \\(\\rbrace\\) : A robust and efficient watermarking framework for generative large language models. In Proceedings of the 33rd USENIX Security Symposium. 1813\u20131830."},{"key":"e_1_3_1_201_2","unstructured":"Xinghua Zhang Bowen Yu Haiyang Yu et\u00a0al. 2023. Wider and deeper llm networks are fairer llm evaluators. arXiv:2308.01862. Retrieved from https:\/\/arxiv.org\/abs\/2308.01862"},{"key":"e_1_3_1_202_2","article-title":"Silent guardian: Protecting text from malicious exploitation by large language models","author":"Zhao Jiawei","year":"2024","unstructured":"Jiawei Zhao, Kejiang Chen, Xiaojian Yuan, et\u00a0al. 2024. Silent guardian: Protecting text from malicious exploitation by large language models. IEEE Transactions on Information Forensics and Security (2024).","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"e_1_3_1_203_2","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1016\/j.comcom.2019.12.016","article-title":"AFA: Adversarial fingerprinting authentication for deep neural networks","volume":"150","author":"Zhao Jingjing","year":"2020","unstructured":"Jingjing Zhao, Qingyue Hu, Gaoyang Liu, et\u00a0al. 2020. AFA: Adversarial fingerprinting authentication for deep neural networks. Computer Communications 150 (2020), 488\u2013497.","journal-title":"Computer Communications"},{"issue":"3","key":"e_1_3_1_204_2","doi-asserted-by":"crossref","first-page":"655","DOI":"10.3390\/electronics13030655","article-title":"Robust soliton distribution-based zero-watermarking for semi-structured power data","volume":"13","author":"Zhao Lei","year":"2024","unstructured":"Lei Zhao, Yunfeng Zou, Chao Xu, Yulong Ma, et\u00a0al. 2024. Robust soliton distribution-based zero-watermarking for semi-structured power data. Electronics 13, 3 (2024), 655.","journal-title":"Electronics"},{"key":"e_1_3_1_205_2","unstructured":"Xuandong Zhao Prabhanjan Ananth Lei Li et\u00a0al. 2023. Provable robust watermarking for ai-generated text. arXiv:2306.17439. Retrieved from https:\/\/arxiv.org\/abs\/2306.17439"},{"key":"e_1_3_1_206_2","volume-title":"Proceedings of the Neurips Safe Generative AI Workshop","author":"Zhao Xuandong","year":"2024","unstructured":"Xuandong Zhao, Lei Li, and Yu-Xiang Wang. 2024. Permute-and-flip: An optimally stable and watermarkable decoder for LLMs. In Proceedings of the Neurips Safe Generative AI Workshop."},{"key":"e_1_3_1_207_2","first-page":"42187","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Zhao Xuandong","year":"2023","unstructured":"Xuandong Zhao, Yu-Xiang Wang, and Lei Li. 2023. Protecting language generation models via invisible watermarking. In Proceedings of the International Conference on Machine Learning. PMLR, 42187\u201342199."},{"issue":"3","key":"e_1_3_1_208_2","doi-asserted-by":"crossref","first-page":"2007","DOI":"10.1109\/TDSC.2020.3043382","article-title":"Protecting decision boundary of machine learning model with differentially private perturbation","volume":"19","author":"Zheng Huadi","year":"2022","unstructured":"Huadi Zheng, Qingqing Ye, Haibo Hu, et\u00a0al. 2022. Protecting decision boundary of machine learning model with differentially private perturbation. IEEE Trans. Dependable Secur. Comput. 19, 3 (2022), 2007\u20132022.","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"e_1_3_1_209_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Zheng Lianmin","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, et\u00a0al. [n.d.]. LMSYS-chat-1M: A large-scale real-world LLM conversation dataset. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_210_2","doi-asserted-by":"crossref","first-page":"2977","DOI":"10.1109\/TIFS.2022.3198267","article-title":"A dnn fingerprint for non-repudiable model ownership identification and piracy detection","volume":"17","author":"Zheng Yue","year":"2022","unstructured":"Yue Zheng, Si Wang, and Chip-Hong Chang. 2022. A dnn fingerprint for non-repudiable model ownership identification and piracy detection. IEEE Transactions on Information Forensics and Security 17 (2022), 2977\u20132989.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"e_1_3_1_211_2","unstructured":"Kun Zhou Yutao Zhu Zhipeng Chen et\u00a0al. 2023. Don\u2019t Make Your LLM an Evaluation Benchmark Cheater. arXiv:2311.01964. Retrieved from https:\/\/arxiv.org\/abs\/2311.01964"},{"issue":"9","key":"e_1_3_1_212_2","article-title":"A reversible watermarking system for medical color images: Balancing capacity, imperceptibility, and robustness","volume":"10","author":"Zhou Xiaoyi","year":"2021","unstructured":"Xiaoyi Zhou, Yue Ma, Qingquan Zhang, et\u00a0al. 2021. A reversible watermarking system for medical color images: Balancing capacity, imperceptibility, and robustness. Electronics 10, 9 (2021).","journal-title":"Electronics"},{"key":"e_1_3_1_213_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Zhu Han","year":"2016","unstructured":"Han Zhu, Mingsheng Long, Jianmin Wang, et\u00a0al. 2016. Deep hashing network for efficient similarity retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_1_214_2","unstructured":"Terry Yue Zhuo Yujin Huang Chunyang Chen et\u00a0al. 2023. Red Teaming ChatGPT via Jailbreaking: Bias Robustness Reliability and Toxicity. arXiv:2301.12867. Retrieved from https:\/\/arxiv.org\/abs\/2301.12867"},{"key":"e_1_3_1_215_2","unstructured":"Andy Zou Zifan Wang Nicholas Carlini et\u00a0al. 2023. Universal and Transferable Adversarial Attacks on Aligned Language Models. arXiv:2307.15043. Retrieved from https:\/\/arxiv.org\/abs\/2307.15043"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3773028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T12:15:46Z","timestamp":1770207346000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773028"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,4]]},"references-count":214,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3773028"],"URL":"https:\/\/doi.org\/10.1145\/3773028","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,4]]},"assertion":[{"value":"2025-02-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}