{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T01:11:58Z","timestamp":1776388318523,"version":"3.51.2"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890065","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Imperceptible Transfer Attack on Large Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Xiaowen","family":"Cai","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology,School of Cyber Science and Engineering,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daizong","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University,Wangxuan Institute of Computer Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runwei","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Liverpool,Department of Electrical Engineering and Electronics,Liverpool,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Cyber Science and Engineering,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547969"},{"key":"ref2","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref3","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3584895"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16307"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3223725"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00452"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_14"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4250-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01474"},{"key":"ref13","article-title":"Harmonizing visual text comprehension and generation","author":"Zhao","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32806"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwad141"},{"key":"ref16","article-title":"Tabpedia: Towards comprehensive visual table understanding with concept synergy","author":"Zhao","year":"2024","journal-title":"NeurIPS"},{"key":"ref17","article-title":"Textsquare: Scaling up text-centric visual instruction tuning","author":"Tang","year":"2024","journal-title":"arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547787"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25251"},{"key":"ref20","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2024","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref22","article-title":"Pandagpt: One model to instruction-follow them all","author":"Su","year":"2023"},{"key":"ref23","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref24","article-title":"A survey of attacks on large vision-language models: Resources, advances, and future trends","author":"Liu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/901"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831129"},{"key":"ref27","article-title":"On evaluating adversarial robustness of large vision-language models","volume":"36","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"An image is worth 1000 lies: Adversarial transferability across prompts on vision-language models","author":"Luo","year":"2024"},{"key":"ref29","article-title":"Image hijacks: Adversarial images can control generative models at runtime","author":"Bailey","year":"2023","journal-title":"arXiv"},{"key":"ref30","article-title":"How robust is google\u2019s bard to adversarial image attacks?","author":"Dong","year":"2023"},{"key":"ref31","article-title":"Instructta: Instruction- tuned targeted attack for large vision-language models","author":"Wang","year":"2023"},{"key":"ref32","article-title":"Stop reasoning! when multimodal llms with chain-of-thought reasoning meets adversarial images","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref33","article-title":"Avibench: Towards evaluating the robustness of large vision-language model on adversarial visual-instructions","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref34","article-title":"Test-time backdoor attacks on multimodal large language models","author":"Lu","year":"2024","journal-title":"arXiv"},{"key":"ref35","article-title":"Imgtrojan: Jailbreaking vision-language models with one image","author":"Tao","year":"2024","journal-title":"arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01319"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_25"},{"key":"ref38","article-title":"Hard-label black-box attacks on 3d point clouds","author":"Liu","year":"2024","journal-title":"arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3304896"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28146"},{"key":"ref41","article-title":"Adversarial attacks on multimodal agents","author":"Wu","year":"2024","journal-title":"arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02325"},{"key":"ref43","article-title":"Pandora\u2019s box: Towards building universal attackers against real-world large vision-language models","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref44","article-title":"Countering adversarial images using input transformations","author":"Guo","year":"2017","journal-title":"arXiv"},{"key":"ref45","article-title":"Mitigating adversarial effects through randomization","author":"Xie","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193449"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_14"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3339130"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.22"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681105"},{"key":"ref52","article-title":"Svit: Scaling up visual instruction tuning","author":"Zhao","year":"2023"},{"key":"ref53","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00396"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890065.pdf?arnumber=10890065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:42Z","timestamp":1774416102000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890065","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}