{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:12:43Z","timestamp":1768281163991,"version":"3.49.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFB2904000"],"award-info":[{"award-number":["2023YFB2904000"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFB2904001"],"award-info":[{"award-number":["2023YFB2904001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2436206"],"award-info":[{"award-number":["U2436206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032021"],"award-info":[{"award-number":["62032021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372406"],"award-info":[{"award-number":["62372406"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LZ25F020005"],"award-info":[{"award-number":["LZ25F020005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2025.3646854","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:40:37Z","timestamp":1766428837000},"page":"870-885","source":"Crossref","is-referenced-by-count":0,"title":["CoGA: A Collaborative Gray-Box Adversarial Attack for Multimodal Language Models"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8778-8842","authenticated-orcid":false,"given":"Tong","family":"Wu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5240-5200","authenticated-orcid":false,"given":"Feng","family":"Lin","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3788-1799","authenticated-orcid":false,"given":"Gaojian","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4706-8817","authenticated-orcid":false,"given":"Tiantian","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5804-3279","authenticated-orcid":false,"given":"Zhibo","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4384-5786","authenticated-orcid":false,"given":"Weizhi","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Computing and Communications, Lancaster University, Lancaster, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7788-9368","authenticated-orcid":false,"given":"Ajian","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1969-2591","authenticated-orcid":false,"given":"Kui","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Vision-language intelligence: Tasks, representation learning, and large models","author":"Li","year":"2022","journal-title":"arXiv:2203.01922"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref3","article-title":"From image to video, what do we need in multimodal LLMs?","author":"Huang","year":"2024","journal-title":"arXiv:2404.11865"},{"key":"ref4","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11203409"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/0600000110"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812060"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3217810"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-023-01045-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3518072"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3574976"},{"key":"ref14","article-title":"Abusing images and sounds for indirect instruction injection in multi-modal LLMs","author":"Bagdasaryan","year":"2023","journal-title":"arXiv:2307.10490"},{"key":"ref15","article-title":"Unifying visualsemantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref16","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019","journal-title":"arXiv:1901.06706"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00395"},{"key":"ref20","article-title":"Survey of vulnerabilities in large language models revealed by adversarial attacks","author":"Shayegani","year":"2023","journal-title":"arXiv:2310.10844"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref22","article-title":"VLATTACK: Multimodal adversarial attacks on vision-language tasks via pre-trained models","author":"Yin","year":"2023","journal-title":"arXiv:2310.04655"},{"key":"ref23","first-page":"54111","article-title":"On evaluating adversarial robustness of large visionlanguage models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhao"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00102"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3520306"},{"key":"ref26","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref27","article-title":"AI and the everything in the whole wide world benchmark","author":"Deborah Raji","year":"2021","journal-title":"arXiv:2111.15366"},{"key":"ref28","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013","journal-title":"arXiv:1312.6199"},{"key":"ref29","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref31","article-title":"Nesterov accelerated gradient and scale invariance for adversarial attacks","author":"Lin","year":"2019","journal-title":"arXiv:1908.06281"},{"key":"ref32","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00816"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00034"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00102"},{"key":"ref37","article-title":"Adversarial GLUE: A multi-task benchmark for robustness evaluation of language models","author":"Wang","year":"2021","journal-title":"arXiv:2111.02840"},{"key":"ref38","article-title":"TextBugger: Generating adversarial text against real-world applications","author":"Li","year":"2018","journal-title":"arXiv:1812.05271"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1103"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.14"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"ref42","article-title":"T3: Treeautoencoder constrained adversarial text generation for targeted attack","author":"Wang","year":"2019","journal-title":"arXiv:1912.10375"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-aacl.41"},{"key":"ref44","article-title":"Universal and transferable adversarial attacks on aligned language models","author":"Zou","year":"2023","journal-title":"arXiv:2307.15043"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00335"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00520"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref48","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref49","article-title":"SALMONN: Towards generic hearing abilities for large language models","author":"Tang","year":"2023","journal-title":"arXiv:2310.13289"},{"key":"ref50","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref51","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv:2310.09478"},{"key":"ref52","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref53","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref57","first-page":"12888","article-title":"BLIP: Bootstrapping languageimage pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909680"},{"key":"ref59","first-page":"18090","article-title":"Pengi: An audio language model for audio tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Deshmukh"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3226905"},{"key":"ref61","article-title":"InstructTA: Instructiontuned targeted attack for large vision-language models","author":"Wang","year":"2023","journal-title":"arXiv:2312.01886"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11310831.pdf?arnumber=11310831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T21:59:34Z","timestamp":1768255174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11310831\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3646854","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}