{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T06:47:39Z","timestamp":1782802059282,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","funder":[{"name":"Institute of Information Engineering,Chinese Academy of Sciences","award":["XDB0690302"],"award-info":[{"award-number":["XDB0690302"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761104","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:18:04Z","timestamp":1762561084000},"page":"1220-1230","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Dangerous Language Habits! Exploiting Code-Mixing for Backdoor Attacks on NLP Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6482-8461","authenticated-orcid":false,"given":"Haotian","family":"Jin","sequence":"first","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4366-9121","authenticated-orcid":false,"given":"Haihui","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1835-1700","authenticated-orcid":false,"given":"Jinchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0749-0028","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6709-0942","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4727-6867","authenticated-orcid":false,"given":"Junhao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118445112.stat01100"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3914"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-1105"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.105"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17140-6_22"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485832.3485837"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73706-5_16"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_9_1","first-page":"5009","article-title":"A unified evaluation of textual backdoor learning: Frameworks and benchmarks","volume":"35","author":"Cui Ganqu","year":"2022","unstructured":"Ganqu Cui, Lifan Yuan, Bingxiang He, Yangyi Chen, Zhiyuan Liu, and Maosong Sun. 2022. A unified evaluation of textual backdoor learning: Frameworks and benchmarks. Advances in Neural Information Processing Systems, Vol. 35 (2022), 5009-5023.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941376"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 2067","author":"Du Wei","year":"2024","unstructured":"Wei Du, Tianjie Ju, Ge Ren, GaoLei Li, and Gongshen Liu. 2024a. Backdoor NLP Models via AI-Generated Text. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 2067-2079."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447968"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412130"},{"key":"e_1_3_2_1_16_1","volume-title":"Word level language identification in english telugu code mixed data. arXiv preprint arXiv:2010.04482","author":"Gundapu Sunil","year":"2020","unstructured":"Sunil Gundapu and Radhika Mamidi. 2020. Word level language identification in english telugu code mixed data. arXiv preprint arXiv:2010.04482 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Daphne Teck Ching Lai, and Rosyzie Anna Apong","author":"Hidayatullah Ahmad Fathan","year":"2022","unstructured":"Ahmad Fathan Hidayatullah, Atika Qazi, Daphne Teck Ching Lai, and Rosyzie Anna Apong. 2022. A systematic review on language identification of code-mixed text: techniques, data availability, challenges, and framework development. IEEE access, Vol. 10 (2022), 122812-122831."},{"key":"e_1_3_2_1_18_1","first-page":"239","volume-title":"Proceedings of the International Conference Recent Advances in Natural Language Processing, Ruslan Mitkov, Galia Angelova, and Kalina Bontcheva (Eds.). INCOMA Ltd. Shoumen, BULGARIA","author":"Jamatia Anupam","year":"2015","unstructured":"Anupam Jamatia, Bj\u00f6rn Gamb\u00e4ck, and Amitava Das. 2015. Part-of-Speech Tagging for Code-Mixed English-Hindi Twitter and Facebook Chat Messages. In Proceedings of the International Conference Recent Advances in Natural Language Processing, Ruslan Mitkov, Galia Angelova, and Kalina Bontcheva (Eds.). INCOMA Ltd. Shoumen, BULGARIA, Hissar, Bulgaria, 239-248. https:\/\/aclanthology.org\/R15-1033\/"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 2482-2491","author":"Joshi Aditya","year":"2016","unstructured":"Aditya Joshi, Ameya Prabhu, Manish Shrivastava, and Vasudeva Varma. 2016. Towards sub-word level compositions for sentiment analysis of hindi-english code mixed text. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 2482-2491."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2052"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.165"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3182979"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_1_24_1","first-page":"3611","volume-title":"31st USENIX Security Symposium (USENIX Security 22)","author":"Pan Xudong","year":"2022","unstructured":"Xudong Pan, Mi Zhang, Beina Sheng, Jiaming Zhu, and Min Yang. 2022. Hidden trigger backdoor attack on {NLP} models via linguistic style manipulation. In 31st USENIX Security Symposium (USENIX Security 22). 3611-3628."},{"key":"e_1_3_2_1_25_1","volume-title":"Semeval-2020 task 9: Overview of sentiment analysis of code-mixed tweets. arXiv preprint arXiv:2008.04277","author":"Patwa Parth","year":"2020","unstructured":"Parth Patwa, Gustavo Aguilar, Sudipta Kar, Suraj Pandey, Srinivas Pykl, Bj\u00f6rn Gamb\u00e4ck, Tanmoy Chakraborty, Thamar Solorio, and Amitava Das. 2020. Semeval-2020 task 9: Overview of sentiment analysis of code-mixed tweets. arXiv preprint arXiv:2008.04277 (2020)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Fanchao Qi Yangyi Chen Mukai Li Yuan Yao Zhiyuan Liu and Maosong Sun. 2021a. ONION: A Simple and Effective Defense Against Textual Backdoor Attacks. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing Marie-Francine Moens Xuanjing Huang Lucia Specia and Scott Wen-tau Yih (Eds.). Association for Computational Linguistics Online and Punta Cana Dominican Republic 9558-9566. doi:10.18653\/v1\/2021.emnlp-main.752","DOI":"10.18653\/v1\/2021.emnlp-main.752"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.374"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Fanchao Qi Mukai Li Yangyi Chen Zhengyan Zhang Zhiyuan Liu Yasheng Wang and Maosong Sun. 2021c. Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) Chengqing Zong Fei Xia Wenjie Li and Roberto Navigli (Eds.). Association for Computational Linguistics Online 443-453. doi:10.18653\/v1\/2021.acl-long.37","DOI":"10.18653\/v1\/2021.acl-long.37"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.377"},{"key":"e_1_3_2_1_31_1","volume-title":"Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi. arXiv preprint arXiv:2309.10272","author":"Raihan Md Nishat","year":"2023","unstructured":"Md Nishat Raihan, Dhiman Goswami, and Antara Mahmud. 2023. Mixed-Distil-BERT: Code-mixed Language Modeling for Bangla, English, and Hindi. arXiv preprint arXiv:2309.10272 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS57517.2022.00086"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.04.080"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2018.8554413"},{"key":"e_1_3_2_1_35_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_36_1","volume-title":"Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, et al., 2022","year":"2022","unstructured":"BigScience Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, et al., 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.441"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Jun Yan Vansh Gupta and Xiang Ren. 2023. BITE: Textual Backdoor Attacks with Iterative Trigger Injection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Anna Rogers Jordan Boyd-Graber and Naoaki Okazaki (Eds.). Association for Computational Linguistics Toronto Canada 12951-12968. doi:10.18653\/v1\/2023.acl-long.725","DOI":"10.18653\/v1\/2023.acl-long.725"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.165"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.833"},{"key":"e_1_3_2_1_41_1","volume-title":"Junbo Jake Zhao, and Yann LeCun","author":"Zhang Xiang","year":"2015","unstructured":"Xiang Zhang, Junbo Jake Zhao, and Yann LeCun. 2015. Character-level Convolutional Networks for Text Classification. In NIPS."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:37:32Z","timestamp":1765503452000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":41,"alternative-id":["10.1145\/3746252.3761104","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761104","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"}}]}}