{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:25:40Z","timestamp":1775096740934,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376024,62171313"],"award-info":[{"award-number":["62376024,62171313"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing National Research Center for Information Science and Technology (BNRist)"},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3685510","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"11175-11183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6049-603X","authenticated-orcid":false,"given":"Yudong","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University & Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-5647","authenticated-orcid":false,"given":"Ruobing","family":"Xie","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2040-7938","authenticated-orcid":false,"given":"Jiansheng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3222-0901","authenticated-orcid":false,"given":"Xingwu","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Macau & Tencent, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716--23736."},{"key":"e_1_3_2_1_2_1","volume-title":"Image hijacks: Adversarial images can control generative models at runtime. arXiv preprint arXiv:2309.00236","author":"Bailey Luke","year":"2023","unstructured":"Luke Bailey, Euan Ong, Stuart Russell, and Scott Emmons. 2023. Image hijacks: Adversarial images can control generative models at runtime. arXiv preprint arXiv:2309.00236 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130401"},{"key":"e_1_3_2_1_4_1","volume-title":"Daphne Ippolito, Florian Tramer, and Ludwig Schmidt.","author":"Carlini Nicholas","year":"2024","unstructured":"Nicholas Carlini, Milad Nasr, Christopher A Choquette-Choo, Matthew Jagielski, Irena Gao, Pang Wei W Koh, Daphne Ippolito, Florian Tramer, and Ludwig Schmidt. 2024. Are aligned neural networks adversarially aligned? Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In 2017 ieee symposium on security and privacy (sp). Ieee 39--57.","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_2_1_6_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2024","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2024. Instructblip: Towards general-purpose vision-language models with instruction tuning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Detecting adversarial examples via neural fingerprinting. arXiv preprint arXiv:1803.03870","author":"Dathathri Sumanth","year":"2018","unstructured":"Sumanth Dathathri, Stephan Zheng, Tianwei Yin, Richard M Murray, and Yisong Yue. 2018. Detecting adversarial examples via neural fingerprinting. arXiv preprint arXiv:1803.03870 (2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"How Robust is Google's Bard to Adversarial Image Attacks? arXiv preprint arXiv:2309.11751","author":"Dong Yinpeng","year":"2023","unstructured":"Yinpeng Dong, Huanran Chen, Jiawei Chen, Zhengwei Fang, Xiao Yang, Yichi Zhang, Yu Tian, Hang Su, and Jun Zhu. 2023. How Robust is Google's Bard to Adversarial Image Attacks? arXiv preprint arXiv:2309.11751 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR, 3564--3575","author":"Gao Ruize","year":"2021","unstructured":"Ruize Gao, Feng Liu, Jingfeng Zhang, Bo Han, Tongliang Liu, Gang Niu, and Masashi Sugiyama. 2021. Maximum mean discrepancy test is aware of adversarial attacks. In International Conference on Machine Learning. PMLR, 3564--3575."},{"key":"e_1_3_2_1_10_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611914"},{"key":"e_1_3_2_1_12_1","volume-title":"Joey Tianyi Zhou, and Peter Szolovits","author":"Jin Di","year":"2019","unstructured":"Di Jin, Zhijing Jin, Joey Tianyi Zhou, and Peter Szolovits. 2019. Is bert really robust? natural language attack on text classification and entailment. arXiv preprint arXiv:1907.11932, Vol. 2 (2019), 10."},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_14_1","volume-title":"Bert-attack: Adversarial attack against bert using bert. arXiv preprint arXiv:2004.09984","author":"Li Linyang","year":"2020","unstructured":"Linyang Li, Ruotian Ma, Qipeng Guo, Xiangyang Xue, and Xipeng Qiu. 2020. Bert-attack: Adversarial attack against bert using bert. arXiv preprint arXiv:2004.09984 (2020)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.615"},{"key":"e_1_3_2_1_16_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"e_1_3_2_1_18_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Luo Haochen","year":"2023","unstructured":"Haochen Luo, Jindong Gu, Fengyuan Liu, and Philip Torr. 2023. An image is worth 1000 lies: Transferability of adversarial images across prompts on vision-language models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350887"},{"key":"e_1_3_2_1_20_1","volume-title":"Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083","author":"Madry Aleksander","year":"2017","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2017. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134057"},{"key":"e_1_3_2_1_22_1","volume-title":"Towards robust detection of adversarial examples. Advances in neural information processing systems","author":"Pang Tianyu","year":"2018","unstructured":"Tianyu Pang, Chao Du, Yinpeng Dong, and Jun Zhu. 2018. Towards robust detection of adversarial examples. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30150"},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612337"},{"key":"e_1_3_2_1_27_1","volume-title":"Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389","author":"Sun Quan","year":"2023","unstructured":"Quan Sun, Yuxin Fang, Ledell Wu, Xinlong Wang, and Yue Cao. 2023. Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Wenhai","year":"2024","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al. 2024. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547989"},{"key":"e_1_3_2_1_30_1","volume-title":"Feature squeezing: Detecting adversarial examples in deep neural networks. arXiv preprint arXiv:1704.01155","author":"Xu Weilin","year":"2017","unstructured":"Weilin Xu, David Evans, and Yanjun Qi. 2017. Feature squeezing: Detecting adversarial examples in deep neural networks. arXiv preprint arXiv:1704.01155 (2017)."},{"key":"e_1_3_2_1_31_1","volume-title":"Vlattack: Multimodal adversarial attacks on vision-language tasks via pre-trained models. arXiv preprint arXiv:2310.04655","author":"Yin Ziyi","year":"2023","unstructured":"Ziyi Yin, Muchao Ye, Tianrong Zhang, Tianyu Du, Jinguo Zhu, Han Liu, Jinghui Chen, Ting Wang, and Fenglong Ma. 2023. Vlattack: Multimodal adversarial attacks on vision-language tasks via pre-trained models. arXiv preprint arXiv:2310.04655 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657781"},{"key":"e_1_3_2_1_34_1","volume-title":"Ngai-Man Man Cheung, and Min Lin","author":"Zhao Yunqing","year":"2024","unstructured":"Yunqing Zhao, Tianyu Pang, Chao Du, Xiao Yang, Chongxuan Li, Ngai-Man Man Cheung, and Min Lin. 2024. On evaluating adversarial robustness of large vision-language models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3685510","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3685510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:28Z","timestamp":1750295848000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3685510"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":35,"alternative-id":["10.1145\/3664647.3685510","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3685510","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}