{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:57Z","timestamp":1780949217535,"version":"3.54.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160603"],"award-info":[{"award-number":["2022ZD0160603"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3664103","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:14Z","timestamp":1770930134000},"page":"8385-8397","source":"Crossref","is-referenced-by-count":0,"title":["GIGAS: Adversarial Attacks on Visual Question Answering With Multi-Modal Generative Models"],"prefix":"10.1109","volume":"36","author":[{"given":"Yunxuan","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3966-511X","authenticated-orcid":false,"given":"Jing","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Minzu University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0688-202X","authenticated-orcid":false,"given":"Tieyong","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Mathematics, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-2659","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8377-0163","authenticated-orcid":false,"given":"Liyan","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291379"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28357"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3541392"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/543"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1610"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23138"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00520"},{"key":"ref10","first-page":"10791","article-title":"Cross-modal learning with adversarial samples","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2303"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28499"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/info16080688"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref16","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3537806"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00754"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01183"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00414"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263054"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00421"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00398"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207310"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00401"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00410"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3546702"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1165"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.495"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3526248"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00222"},{"key":"ref37","article-title":"Exploring transferability of multimodal adversarial samples for vision-language pre-training models with contrastive learning","author":"Wang","year":"2023","journal-title":"arXiv:2308.12636"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00502"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref40","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref41","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref44","first-page":"61501","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref45","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2977695"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00650"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/453"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.707"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref54","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref55","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref56","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref57","first-page":"25994","article-title":"Multi-grained vision language pretraining: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zeng"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref60","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00034"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2253"},{"key":"ref64","first-page":"2900","article-title":"X-transfer attacks: Towards super transferable adversarial attacks on CLIP","volume-title":"Proc. ICML","author":"Huang"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1103"},{"key":"ref66","article-title":"An LLM can fool itself: A prompt-based adversarial attack","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00102"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00390"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00645"},{"key":"ref70","first-page":"43685","article-title":"Robust CLIP: Unsupervised adversarial fine-tuning of vision embeddings for robust large vision-language models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Schlarmann"},{"key":"ref71","article-title":"Robust-LLaVA: On the effectiveness of large-scale robust image encoders for multi-modal large language models","author":"Malik","year":"2025","journal-title":"arXiv:2502.01576"},{"key":"ref72","article-title":"Pathvqa: 30000+ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv:2003.10286"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11395335.pdf?arnumber=11395335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:41Z","timestamp":1780948481000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11395335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":73,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3664103","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}