{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:36:45Z","timestamp":1784237805560,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2207231"],"award-info":[{"award-number":["CNS-2207231"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Intelligence Advanced Research Projects Activity","doi-asserted-by":"publisher","award":["W91NF-20-C-0034"],"award-info":[{"award-number":["W91NF-20-C-0034"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1145\/3658644.3690325","type":"proceedings-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T12:19:20Z","timestamp":1733746760000},"page":"1285-1299","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6224-791X","authenticated-orcid":false,"given":"Xiaoyi","family":"Chen","sequence":"first","affiliation":[{"name":"Indiana University Bloomington, Bloomington, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3377-6975","authenticated-orcid":false,"given":"Siyuan","family":"Tang","sequence":"additional","affiliation":[{"name":"Indiana University Bloomington, Bloomington, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8059-6718","authenticated-orcid":false,"given":"Rui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Indiana University Bloomington, Bloomington, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6289-1374","authenticated-orcid":false,"given":"Shijun","family":"Yan","sequence":"additional","affiliation":[{"name":"JD Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5037-8617","authenticated-orcid":false,"given":"Lei","family":"Jin","sequence":"additional","affiliation":[{"name":"JD Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7620-4142","authenticated-orcid":false,"given":"Zihao","family":"Wang","sequence":"additional","affiliation":[{"name":"Indiana University Bloomington, Bloomington, Indiana, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9499-2298","authenticated-orcid":false,"given":"Liya","family":"Su","sequence":"additional","affiliation":[{"name":"JD Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7208-3392","authenticated-orcid":false,"given":"Zhikun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0607-4946","authenticated-orcid":false,"given":"XiaoFeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Indiana University Bloomington, Bloomington, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8963-8155","authenticated-orcid":false,"given":"Haixu","family":"Tang","sequence":"additional","affiliation":[{"name":"Indiana University Bloomington, Bloomington, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2015. Enron Email Dataset. https:\/\/www.cs.cmu.edu\/~enron\/."},{"key":"e_1_3_2_1_2_1","unstructured":"2024. Ai4Privacy. https:\/\/huggingface.co\/datasets\/ai4privacy\/pii-masking-300k."},{"key":"e_1_3_2_1_3_1","unstructured":"2024. Find Emails. https:\/\/www.findemails.com\/."},{"key":"e_1_3_2_1_4_1","unstructured":"2024. findthatlead. https:\/\/findthatlead.com\/en\/."},{"key":"e_1_3_2_1_5_1","unstructured":"2024. Fine-tune a Llama 2 model in Azure AI Studio. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-studio\/how-to\/fine-tune-model-llama."},{"key":"e_1_3_2_1_6_1","unstructured":"2024. Fine-tuning - OpenAI. https:\/\/platform.openai.com\/docs\/guides\/finetuning."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_8_1","volume-title":"NAACL 2019, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). 54--59","author":"Akbik Alan","year":"2019","unstructured":"Alan Akbik, Tanja Bergmann, Duncan Blythe, Kashif Rasul, Stefan Schweter, and Roland Vollgraf. 2019. FLAIR: An easy-to-use framework for state-of-the-art NLP. In NAACL 2019, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). 54--59."},{"key":"e_1_3_2_1_9_1","unstructured":"Alex Albert. 2023. Jailbreak Chat. https:\/\/www.jailbreakchat.com\/prompt\/4f37a029--9dff-4862-b323-c96a5504de5d"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.05862"},{"key":"e_1_3_2_1_11_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_12_1","volume-title":"Quantifying memorization across neural language models. arXiv preprint arXiv:2202.07646","author":"Carlini Nicholas","year":"2022","unstructured":"Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang. 2022. Quantifying memorization across neural language models. arXiv preprint arXiv:2202.07646 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021. Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21). 2633--2650."},{"key":"e_1_3_2_1_14_1","volume-title":"Neural legal judgment prediction in English. arXiv preprint arXiv:1906.02059","author":"Chalkidis Ilias","year":"2019","unstructured":"Ilias Chalkidis, Ion Androutsopoulos, and Nikolaos Aletras. 2019. Neural legal judgment prediction in English. arXiv preprint arXiv:1906.02059 (2019)."},{"key":"e_1_3_2_1_15_1","volume-title":"Recall and learn: Fine-tuning deep pretrained language models with less forgetting. arXiv preprint arXiv:2004.12651","author":"Chen Sanyuan","year":"2020","unstructured":"Sanyuan Chen, Yutai Hou, Yiming Cui, Wanxiang Che, Ting Liu, and Xiangzhan Yu. 2020. Recall and learn: Fine-tuning deep pretrained language models with less forgetting. arXiv preprint arXiv:2004.12651 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"An embarrassingly simple approach for transfer learning from pretrained language models. arXiv preprint arXiv:1902.10547","author":"Chronopoulou Alexandra","year":"2019","unstructured":"Alexandra Chronopoulou, Christos Baziotis, and Alexandros Potamianos. 2019. An embarrassingly simple approach for transfer learning from pretrained language models. arXiv preprint arXiv:1902.10547 (2019)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li XuezhiWang Mostafa Dehghani Siddhartha Brahma AlbertWebson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Sharan Narang Gaurav Mishra Adams Yu Vincent Y. Zhao Yanping Huang Andrew M. Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. CoRR abs\/2210.11416 (2022). https:\/\/doi.org\/10.48550\/arXiv.2210.11416 arXiv:2210.11416","DOI":"10.48550\/arXiv.2210.11416"},{"key":"e_1_3_2_1_18_1","volume-title":"Safe rlhf: Safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773","author":"Dai Josef","year":"2023","unstructured":"Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, and Yaodong Yang. 2023. Safe rlhf: Safe reinforcement learning from human feedback. arXiv preprint arXiv:2310.12773 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_28"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.102"},{"key":"e_1_3_2_1_21_1","volume-title":"Are large pretrained language models leaking your personal information? arXiv preprint arXiv:2205.12628","author":"Huang Jie","year":"2022","unstructured":"Jie Huang, Hanyin Shao, and Kevin Chen-Chuan Chang. 2022. Are large pretrained language models leaking your personal information? arXiv preprint arXiv:2205.12628 (2022)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 3519--3529","author":"Kornblith Simon","year":"2019","unstructured":"Simon Kornblith, Mohammad Norouzi, Honglak Lee, and Geoffrey Hinton. 2019. Similarity of neural network representations revisited. In International conference on machine learning. PMLR, 3519--3529."},{"key":"e_1_3_2_1_24_1","volume-title":"Multi-step jailbreaking privacy attacks on chatgpt. arXiv preprint arXiv:2304.05197","author":"Li Haoran","year":"2023","unstructured":"Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, and Yangqiu Song. 2023. Multi-step jailbreaking privacy attacks on chatgpt. arXiv preprint arXiv:2304.05197 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_26_1","volume-title":"Autodan: Generating stealthy jailbreak prompts on aligned large language models. arXiv preprint arXiv:2310.04451","author":"Liu Xiaogeng","year":"2023","unstructured":"Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao. 2023. Autodan: Generating stealthy jailbreak prompts on aligned large language models. arXiv preprint arXiv:2310.04451 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Analyzing Leakage of Personally Identifiable Information in Language Models. In 2023 IEEE Symposium on Security and Privacy (SP). IEEE Computer Society, 346--363","author":"Lukas Nils","year":"2023","unstructured":"Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, and Santiago Zanella-B\u00e9guelin. 2023. Analyzing Leakage of Personally Identifiable Information in Language Models. In 2023 IEEE Symposium on Security and Privacy (SP). IEEE Computer Society, 346--363."},{"key":"e_1_3_2_1_28_1","volume-title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747","author":"Luo Yun","year":"2023","unstructured":"Yun Luo, Zhen Yang, Fandong Meng, Yafu Li, Jie Zhou, and Yue Zhang. 2023. An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Learning Differentially Private Recurrent Language Models. In International Conference on Learning Representations.","author":"McMahan Brendan","year":"2018","unstructured":"HBrendan McMahan, Daniel Ramage, Kunal Talwar, and Li Zhang. 2018. Learning Differentially Private Recurrent Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","volume-title":"Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843","author":"Merity Stephen","year":"2016","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)."},{"key":"e_1_3_2_1_31_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul F. Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In NeurIPS. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/b1efde53be364a73914f58805a001731-Abstract-Conference.html"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.129"},{"key":"e_1_3_2_1_33_1","volume-title":"Exploiting novel gpt-4 apis. arXiv preprint arXiv:2312.14302","author":"Pelrine Kellin","year":"2023","unstructured":"Kellin Pelrine, Mohammad Taufeeque, Michal Zajac, Euan McLean, and Adam Gleave. 2023. Exploiting novel gpt-4 apis. arXiv preprint arXiv:2312.14302 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"MLLM-Protector: Ensuring MLLM?s Safety without Hurting Performance. arXiv preprint arXiv:2401.02906","author":"Pi Renjie","year":"2024","unstructured":"Renjie Pi, Tianyang Han, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, and Tong Zhang. 2024. MLLM-Protector: Ensuring MLLM?s Safety without Hurting Performance. arXiv preprint arXiv:2401.02906 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Even When Users Do Not Intend To! arXiv preprint arXiv:2310.03693","author":"Qi Xiangyu","year":"2023","unstructured":"Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson. 2023. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! arXiv preprint arXiv:2310.03693 (2023)."},{"key":"e_1_3_2_1_36_1","unstructured":"Alec Radford JeffreyWu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_37_1","unstructured":"Alec Radford JeffreyWu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_38_1","volume-title":"Multitask Prompted Training Enables Zero-Shot Task Generalization. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Sanh Victor","year":"2022","unstructured":"Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey, M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal V. Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian Jiang, HanWang, Matteo Manica, Sheng Shen, Zheng Xin Yong, Harshit Pandey, Rachel Bawden, ThomasWang, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Andrea Santilli, Thibault F\u00e9vry, Jason Alan Fries, Ryan Teehan, Teven Le Scao, Stella Biderman, Leo Gao, Thomas Wolf, and Alexander M. Rush. 2022. Multitask Prompted Training Enables Zero-Shot Task Generalization. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. https:\/\/openreview.net\/forum?id=9Vrb9D0WI4"},{"key":"e_1_3_2_1_39_1","volume-title":"Are emergent abilities of Large Language Models a mirage? arXiv preprint arXiv:2304.15004","author":"Schaeffer Rylan","year":"2023","unstructured":"Rylan Schaeffer, Brando Miranda, and Sanmi Koyejo. 2023. Are emergent abilities of Large Language Models a mirage? arXiv preprint arXiv:2304.15004 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models. arXiv preprint arXiv:2308.03825","author":"Shen Xinyue","year":"2023","unstructured":"Xinyue Shen, Zeyuan Chen, Michael Backes, Yun Shen, and Yang Zhang. 2023. \" Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models. arXiv preprint arXiv:2308.03825 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.03825"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 22nd ACM SIGSAC conference on computer and communications security. 1310--1321","author":"Shokri Reza","year":"2015","unstructured":"Reza Shokri and Vitaly Shmatikov. 2015. Privacy-preserving deep learning. In Proceedings of the 22nd ACM SIGSAC conference on computer and communications security. 1310--1321."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2023.100494"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.14525"},{"key":"e_1_3_2_1_45_1","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Tirumala Kushal","year":"2022","unstructured":"Kushal Tirumala, Aram Markosyan, Luke Zettlemoyer, and Armen Aghajanyan. 2022. Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models. In Advances in Neural Information Processing Systems, Vol. 35. Curran Associates, Inc., 38274--38290. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/fa0509f4dab6807e2cb465715bf2d249-Paper-Conference.pdf"},{"key":"e_1_3_2_1_46_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_47_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Will we run out of data? An analysis of the limits of scaling datasets in Machine Learning. arXiv preprint arXiv:2211.04325","author":"Villalobos Pablo","year":"2022","unstructured":"Pablo Villalobos, Jaime Sevilla, Lennart Heim, Tamay Besiroglu, Marius Hobbhahn, and Anson Ho. 2022. Will we run out of data? An analysis of the limits of scaling datasets in Machine Learning. arXiv preprint arXiv:2211.04325 (2022)."},{"key":"e_1_3_2_1_49_1","volume-title":"Workshop on Efficient Systems for Foundation Models@ ICML2023","author":"Wang Xinyi","year":"2023","unstructured":"Xinyi Wang, Wanrong Zhu, Michael Saxon, Mark Steyvers, and William Yang Wang. 2023. Large language models are implicitly topic models: Explaining and finding good demonstrations for in-context learning. In Workshop on Efficient Systems for Foundation Models@ ICML2023."},{"key":"e_1_3_2_1_50_1","volume-title":"Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems 36","author":"Wei Alexander","year":"2024","unstructured":"Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2024. Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022. Finetuned Language Models are Zero-Shot Learners. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. https:\/\/openreview.net\/forum?id=gEZrGCozdqR"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00765-8"},{"key":"e_1_3_2_1_53_1","volume-title":"Removing rlhf protections in gpt-4 via fine-tuning. arXiv preprint arXiv:2311.05553","author":"Zhan Qiusi","year":"2023","unstructured":"Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, and Daniel Kang. 2023. Removing rlhf protections in gpt-4 via fine-tuning. arXiv preprint arXiv:2311.05553 (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation. arXiv preprint arXiv:2307.04401","author":"Zhang Zhexin","year":"2023","unstructured":"Zhexin Zhang, Jiaxin Wen, and Minlie Huang. 2023. ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation. arXiv preprint arXiv:2307.04401 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models. arXiv preprint arXiv:2212.04687","author":"Zhu Rui","year":"2022","unstructured":"Rui Zhu, Di Tang, Siyuan Tang, XiaoFeng Wang, and Haixu Tang. 2022. Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models. arXiv preprint arXiv:2212.04687 (2022)."}],"event":{"name":"CCS '24: ACM SIGSAC Conference on Computer and Communications Security","location":"Salt Lake City UT USA","acronym":"CCS '24","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658644.3690325","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658644.3690325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T06:05:36Z","timestamp":1755842736000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658644.3690325"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":55,"alternative-id":["10.1145\/3658644.3690325","10.1145\/3658644"],"URL":"https:\/\/doi.org\/10.1145\/3658644.3690325","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2024-12-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}