{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:16:56Z","timestamp":1765502216983,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS 2046086"],"award-info":[{"award-number":["IIS 2046086"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-24-1-0397"],"award-info":[{"award-number":["W911NF-24-1-0397"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3760886","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T01:03:42Z","timestamp":1762563822000},"page":"4857-4861","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0212-2967","authenticated-orcid":false,"given":"Sri Durga Sai Sowmya","family":"Kadali","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3411-8483","authenticated-orcid":false,"given":"Evangelos","family":"Papalexakis","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. Implementation of the proposed CoCoTen method. https:\/\/github.com\/sowmyakadali009\/CoCoTen-Detecting-Adversarial-Inputsto- LLMs-via-Contextual-Co-occurrence-Tensors.git"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Bocheng Chen Advait Paliwal and Qiben Yan. 2023. Jailbreaker in Jail: Moving Target Defense for Large Language Models. arXiv:2310.02417 [cs.CR] https:\/\/arxiv.org\/abs\/2310.02417","DOI":"10.1145\/3605760.3623764"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24188"},{"key":"e_1_3_2_1_4_1","unstructured":"Jack Hao. [n.d.]. Jailbreak Classification Dataset. https:\/\/huggingface.co\/datasets\/jackhhao\/jailbreak-classification"},{"key":"e_1_3_2_1_5_1","volume-title":"Micah Goldblum, Aniruddha Saha, Jonas Geiping, and Tom Goldstein.","author":"Jain Neel","year":"2023","unstructured":"Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, and Tom Goldstein. 2023. Baseline Defenses for Adversarial Attacks Against Aligned Language Models. arXiv:2309.00614 [cs.LG] https:\/\/arxiv.org\/abs\/2309.00614"},{"key":"e_1_3_2_1_6_1","unstructured":"Liwei Jiang Kavel Rao Seungju Han Allyson Ettinger Faeze Brahman Sachin Kumar Niloofar Mireshghallah Ximing Lu Maarten Sap Yejin Choi and Nouha Dziri. 2024. WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models. arXiv:2406.18510 [cs.CL] https:\/\/arxiv.org\/abs\/2406.18510"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689217.3690618"},{"key":"e_1_3_2_1_8_1","volume-title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge. arXiv:2404.05880 [cs.CL] https:\/\/arxiv.org\/abs\/2404.05880","author":"Lu Weikai","year":"2024","unstructured":"Weikai Lu, Ziqian Zeng, Jianwei Wang, Zhengdong Lu, Zelin Chen, Huiping Zhuang, and Cen Chen. 2024. Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge. arXiv:2404.05880 [cs.CL] https:\/\/arxiv.org\/abs\/2404.05880"},{"key":"e_1_3_2_1_9_1","unstructured":"Evangelos E. Papalexakis. 2018. Unsupervised Content-Based Identification of Fake News Articles with Tensor Decomposition Ensembles. https:\/\/api.semanticscholar.org\/CorpusID:26675959"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Benji Peng Ziqian Bi Qian Niu Ming Liu Pohsun Feng Tianyang Wang Lawrence K. Q. Yan Yizhu Wen Yichao Zhang and Caitlyn Heqi Yin. 2024. Jailbreaking and Mitigation of Vulnerabilities in Large Language Models. arXiv:2410.15236 [cs.CR] https:\/\/arxiv.org\/abs\/2410.15236","DOI":"10.31219\/osf.io\/z8jk3"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651513"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Xinyue Shen Zeyuan Chen Michael Backes Yun Shen and Yang Zhang. 2024. ''Do Anything Now'': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models. arXiv:2308.03825 [cs.CR] https:\/\/arxiv.org\/abs\/2308.03825","DOI":"10.1145\/3658644.3670388"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670388"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2690524"},{"key":"e_1_3_2_1_15_1","volume-title":"Ahmed Hassan Awadallah, and Bo Li","author":"Wang Boxin","year":"2021","unstructured":"Boxin Wang, Chejian Xu, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao, Ahmed Hassan Awadallah, and Bo Li. 2021. Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=GF9cSKI3A_q"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.157"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Yihan Wang Zhouxing Shi Andrew Bai and Cho-Jui Hsieh. 2024. Defending LLMs against Jailbreaking Attacks via Backtranslation. arXiv:2402.16459 [cs.CL] https:\/\/arxiv.org\/abs\/2402.16459","DOI":"10.18653\/v1\/2024.findings-acl.948"},{"key":"e_1_3_2_1_18_1","volume-title":"Jailbroken: How Does LLM Safety Training Fail? arXiv:2307.02483 [cs.LG] https:\/\/arxiv.org\/abs\/2307.02483","author":"Wei Alexander","year":"2023","unstructured":"Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2023. Jailbroken: How Does LLM Safety Training Fail? arXiv:2307.02483 [cs.LG] https:\/\/arxiv.org\/abs\/2307.02483"},{"key":"e_1_3_2_1_19_1","unstructured":"Zihao Xu Yi Liu Gelei Deng Yuekang Li and Stjepan Picek. 2024. A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models. arXiv:2402.13457 [cs.CR] https:\/\/arxiv.org\/abs\/2402.13457"},{"key":"e_1_3_2_1_20_1","unstructured":"Sibo Yi Yule Liu Zhen Sun Tianshuo Cong Xinlei He Jiaxing Song Ke Xu and Qi Li. 2024. Jailbreak Attacks and Defenses Against Large Language Models: A Survey. arXiv:2407.04295 [cs.CR] https:\/\/arxiv.org\/abs\/2407.04295"},{"key":"e_1_3_2_1_21_1","volume-title":"Bach","author":"Yong Zheng-Xin","year":"2024","unstructured":"Zheng-Xin Yong, Cristina Menghini, and Stephen H. Bach. 2024. Low-Resource Languages Jailbreak GPT-4. arXiv:2310.02446 [cs.CL] https:\/\/arxiv.org\/abs\/2310.02446"},{"key":"e_1_3_2_1_22_1","unstructured":"Xiaoyu Zhang Cen Zhang Tianlin Li Yihao Huang Xiaojun Jia Ming Hu Jie Zhang Yang Liu Shiqing Ma and Chao Shen. 2024. JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks. arXiv:2312.10766 [cs.CR] https:\/\/arxiv.org\/abs\/2312.10766"},{"key":"e_1_3_2_1_23_1","unstructured":"Yuqi Zhang Liang Ding Lefei Zhang and Dacheng Tao. 2024. Intention Analysis Makes LLMs A Good Jailbreak Defender. arXiv:2401.06561 [cs.CL] https:\/\/arxiv.org\/abs\/2401.06561"},{"key":"e_1_3_2_1_24_1","unstructured":"Xuandong Zhao Xianjun Yang Tianyu Pang Chao Du Lei Li Yu-Xiang Wang and William Yang Wang. 2024. Weak-to-Strong Jailbreaking on Large Language Models. arXiv:2401.17256 [cs.CL] https:\/\/arxiv.org\/abs\/2401.17256"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19--1669"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3746252.3760886","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3760886","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3760886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:15:01Z","timestamp":1765502101000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3760886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":25,"alternative-id":["10.1145\/3746252.3760886","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3760886","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}