{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:46:07Z","timestamp":1765309567383,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","funder":[{"name":"National Natural Science Foun- dation of China","award":["62476224"],"award-info":[{"award-number":["62476224"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754463","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"13489-13491","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7140-0420","authenticated-orcid":false,"given":"Wei","family":"Cai","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China and Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-756X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China and Northwest Polytechnical University, Xian, Shanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4688-1380","authenticated-orcid":false,"given":"Yuchu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, Jiangsu, China and Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4881-2406","authenticated-orcid":false,"given":"Tianle","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-4197","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models. arXiv preprint arXiv:2003.11743","author":"Agarwal Pranav","year":"2020","unstructured":"Pranav Agarwal, Alejandro Betancourt, Vana Panagiotou, and Natalia D\u00edaz-Rodr\u00edguez. 2020. Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models. arXiv preprint arXiv:2003.11743 (2020)."},{"key":"e_1_3_2_1_2_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_3_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Sh?ie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01350"},{"key":"e_1_3_2_1_5_1","unstructured":"Qingxiu Dong Lei Li Damai Dai Ce Zheng Jingyuan Ma Rui Li Heming Xia Jingjing Xu ZhiyongWu Tianyu Liu et al. 2022. Asurvey on in-context learning. arXiv preprint arXiv:2301.00234 (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"Mimic In-Context Learning for Multimodal Tasks. arXiv preprint arXiv:2504.08851","author":"Jiang Yuchu","year":"2025","unstructured":"Yuchu Jiang, Jiale Fu, Chenduo Hao, Xinting Hu, Yingzhe Peng, Xin Geng, and Xu Yang. 2025. Mimic In-Context Learning for Multimodal Tasks. arXiv preprint arXiv:2504.08851 (2025)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Alina Kuznetsova Hassan Rom Neil Alldrin Jasper U?lings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Alexander Kolesnikov et al. 2020. The open images dataset v4: Unified image classification object detection and visual relationship detection at scale. International journal of computer vision 128 7 (2020) 1956--1981.","DOI":"10.1007\/s11263-020-01316-z"},{"key":"e_1_3_2_1_8_1","volume-title":"European Conference on Computer Vision. Springer, 174--189","author":"Li Yifan","year":"2024","unstructured":"Yifan Li, Hangyu Guo, Kun Zhou,Wayne Xin Zhao, and Ji-RongWen. 2024. Images are achilles' heel of alignment: Exploiting visual vulnerabilities for jailbreaking multimodal large language models. In European Conference on Computer Vision. Springer, 174--189."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_10_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems 36 (2023), 34892--34916."},{"key":"e_1_3_2_1_11_1","volume-title":"European Conference on Computer Vision. Springer, 386--403","author":"Liu Xin","year":"2024","unstructured":"Xin Liu, Yichen Zhu, Jindong Gu, Yunshi Lan, Chao Yang, and Yu Qiao. 2024. Mm-safetybench: A benchmark for safety evaluation of multimodal large language models. In European Conference on Computer Vision. Springer, 386--403."},{"key":"e_1_3_2_1_12_1","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"e_1_3_2_1_13_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, ShiboWang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, ShiboWang, et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_14_1","first-page":"3563","article-title":"Safe inputs but unsafe output: Benchmarking cross-modality safety alignment of large vision-language models","volume":"2025","author":"Ye Xingsong","year":"2025","unstructured":"SiyinWang, Xingsong Ye, Qinyuan Cheng, Junwen Duan, Shimin Li, Jinlan Fu, Xipeng Qiu, and Xuan-Jing Huang. 2025. Safe inputs but unsafe output: Benchmarking cross-modality safety alignment of large vision-language models. In Findings of the Association for Computational Linguistics: NAACL 2025. 3563--3605.","journal-title":"Findings of the Association for Computational Linguistics: NAACL"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:42:22Z","timestamp":1765309342000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":14,"alternative-id":["10.1145\/3746027.3754463","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754463","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}