{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:27:04Z","timestamp":1773966424773,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["U23B2031"],"award-info":[{"award-number":["U23B2031"]}],"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":["62306098"],"award-info":[{"award-number":["62306098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Central Universities","award":["JZ2024HGTB0256"],"award-info":[{"award-number":["JZ2024HGTB0256"]}]},{"name":"Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation"},{"DOI":"10.13039\/501100002729","name":"Anhui University","doi-asserted-by":"publisher","award":["MMC202412"],"award-info":[{"award-number":["MMC202412"]}],"id":[{"id":"10.13039\/501100002729","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Singapore through its AI Singapore Programme","award":["AISG2-RP-2021-022"],"award-info":[{"award-number":["AISG2-RP-2021-022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3581811","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T13:29:00Z","timestamp":1750426140000},"page":"6410-6421","source":"Crossref","is-referenced-by-count":4,"title":["Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-Training Models With Contrastive Learning"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5621-6310","authenticated-orcid":false,"given":"Youze","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0639-2012","authenticated-orcid":false,"given":"Wenbo","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1299-683X","authenticated-orcid":false,"given":"Yinpeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8294-6315","authenticated-orcid":false,"given":"Hang","family":"Su","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref3","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","year":"2022"},{"key":"ref4","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/759"},{"key":"ref7","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3673902"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00444"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23138"},{"key":"ref12","first-page":"8342","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow","year":"2015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"ref15","first-page":"85","article-title":"Backpropagating linearly improves transferability of adversarial examples","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Guo","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00761"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref19","first-page":"54111","article-title":"On evaluating adversarial robustness of large vision-language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00276"},{"key":"ref21","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Sun","year":"2023"},{"key":"ref22","first-page":"2002","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu","year":"2023"},{"key":"ref23","first-page":"277","article-title":"CLEAR: Contrastive learning for sentence representation","volume-title":"Proc. 18th Int. Conf. Natural Lang. Process.","author":"Wu"},{"key":"ref24","first-page":"23102","article-title":"COCO-LM: Correcting and contrasting text sequences for language model pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Meng","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3544558"},{"key":"ref26","first-page":"1024","article-title":"Nesterov accelerated gradient and scale invariance for adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00196"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00754"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3211736"},{"key":"ref30","first-page":"2835","article-title":"TransFool: An adversarial attack against neural machine translation models","author":"Sadrizadeh","year":"2023","journal-title":"IEEE Trans. Mach. Learn. Res."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126733"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.464"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_42"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00222"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3079723"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3315550"},{"key":"ref40","first-page":"1024","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2016"},{"key":"ref41","first-page":"820","article-title":"BERTscore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.12"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref46","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012"},{"key":"ref47","first-page":"29845","article-title":"Boosting the transferability of adversarial attacks with reverse adversarial perturbation","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Qin","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11045507.pdf?arnumber=11045507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:20:28Z","timestamp":1759234828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3581811","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}