{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T08:32:30Z","timestamp":1783585950695,"version":"3.55.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171248,62301189"],"award-info":[{"award-number":["62171248,62301189"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00390","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4090-4100","source":"Crossref","is-referenced-by-count":6,"title":["One Perturbation is Enough: On Generating Universal Adversarial Perturbations Against Vision-Language Pre-Training Models"],"prefix":"10.1109","author":[{"given":"Hao","family":"Fang","sequence":"first","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Kong","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen ShenNong Information Technology Co., Ltd.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu-Tao","family":"Xia","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28963"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref5","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682430"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00175"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00458"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01574"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3416849"},{"key":"ref16","article-title":"Adversarial robustness for visual grounding of multimodal large language models","volume-title":"ICLR 2024 Workshop on Reliable and Responsible Foundation Models","author":"Gao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00390"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref22","article-title":"On single source robustness in deep fusion models","volume":"32","author":"Kim","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref25","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref26","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00409"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2861800"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00465"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_7"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3345136"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00102"},{"key":"ref41","article-title":"A comprehensive survey on cross-modal retrieval","author":"Wang","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00335"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2025.3589127"},{"key":"ref47","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"International conference on machine learning","author":"Zeng"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657781"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00401"},{"key":"ref51","article-title":"Stealthy shield defense: A conditional mutual information-based approach against blackbox model inversion attacks","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhuang"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444077.pdf?arnumber=11444077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:21Z","timestamp":1777530141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444077\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00390","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}