{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:11:51Z","timestamp":1773137511755,"version":"3.50.1"},"reference-count":60,"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\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ23018"],"award-info":[{"award-number":["JQ23018"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L252032"],"award-info":[{"award-number":["L252032"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"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":["62276257"],"award-info":[{"award-number":["62276257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3639961","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:18Z","timestamp":1764787398000},"page":"1663-1676","source":"Crossref","is-referenced-by-count":0,"title":["Invisible Backdoor Attack With Siamese Tuning on Pre-Trained Vision-Language Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1018-6425","authenticated-orcid":false,"given":"Bing","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9488-2208","authenticated-orcid":false,"given":"Shengsheng","family":"Qian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref2","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref4","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530068"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref10","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12444-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/759"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3280734"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.69"},{"key":"ref16","article-title":"Exploring the versatility of zero-shot CLIP for interstitial lung disease classification","author":"Uden","year":"2023"},{"key":"ref17","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3487890"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3559758"},{"key":"ref20","first-page":"469","article-title":"BBAS: Towards large scale effective ensemble adversarial attacks against deep neural network learning","volume-title":"Inf. Sci.","volume":"569","author":"Shen","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3411936"},{"key":"ref22","first-page":"1","article-title":"Poisoning and backdooring contrastive learning","volume-title":"Proc. Tenth Int. Conf. Learn. Representations","author":"Carlini","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833644"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01494"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01178"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363216"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3359789.3359790"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00031"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3311646"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3227416"},{"key":"ref33","article-title":"Effective backdoor mitigation in vision-language models depends on the pre-training objective","volume":"2025","author":"Verma","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref34","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3396272"},{"key":"ref39","article-title":"A zero-\/few-shot anomaly classification and segmentation method for CVPR 2023 vand workshop challenge tracks 1&2: 1st place on zero-shot ad and 4th place on few-shot ad","author":"Chen","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref41","first-page":"1","article-title":"AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection","author":"Zhou","year":"2024","journal-title":"ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16184"},{"key":"ref43","article-title":"BadNets: Identifying vulnerabilities in the machine learning model supply chain","author":"Gu","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3412388"},{"key":"ref45","first-page":"13327","article-title":"Backdoor attacks on self-supervised learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Saha","year":"2021"},{"key":"ref46","article-title":"A survey of recent backdoor attacks and defenses in large language models","volume-title":"Trans. Mach. Learn. Res.","author":"Zhao","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592038"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_27"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3182979"},{"key":"ref50","first-page":"39299","article-title":"Data poisoning attacks against multimodal encoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/283"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00220"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_23"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref56","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref57","first-page":"1","article-title":"Poisoning and backdooring contrastive learning","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Carlini","year":"2022"},{"key":"ref58","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref59","first-page":"1","article-title":"Visual classification via description from large language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Menon","year":"2023"},{"key":"ref60","first-page":"39299","article-title":"Data poisoning attacks against multimodal encoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2022"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11275936.pdf?arnumber=11275936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:59:29Z","timestamp":1773086369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11275936\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3639961","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}