{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:22:10Z","timestamp":1771611730980,"version":"3.50.1"},"reference-count":43,"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":[{"name":"National Key Research and Development Program of China","award":["2022ZD0119200"],"award-info":[{"award-number":["2022ZD0119200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025604"],"award-info":[{"award-number":["62025604"]}],"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":["62411540034"],"award-info":[{"award-number":["62411540034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Ningbo Science and Technology Innovation 2025 Major Project","doi-asserted-by":"publisher","award":["2025Z027"],"award-info":[{"award-number":["2025Z027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3626950","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:00:59Z","timestamp":1761847259000},"page":"12404-12416","source":"Crossref","is-referenced-by-count":2,"title":["CleanerCLIP: Fine-Grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7069-9816","authenticated-orcid":false,"given":"Yuan","family":"Xun","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6154-0233","authenticated-orcid":false,"given":"Siyuan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Queenstown, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2018-9344","authenticated-orcid":false,"given":"Xiaojun","family":"Jia","sequence":"additional","affiliation":[{"name":"Cyber Security Research Centre @ NTU, Nanyang Technological University, Jurong West, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9510-418X","authenticated-orcid":false,"given":"Xinwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7397-2714","authenticated-orcid":false,"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7141-708X","authenticated-orcid":false,"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.14447"},{"key":"ref3","article-title":"On similarity","author":"Costa","year":"2021","journal-title":"arXiv:2111.02803"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-661"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.56"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref7","article-title":"Backdoor attacks and countermeasures on deep learning: A comprehensive review","author":"Gao","year":"2020","journal-title":"arXiv:2007.10760"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01298"},{"key":"ref10","article-title":"Poisoning and backdooring contrastive learning","author":"Carlini","year":"2021","journal-title":"arXiv:2106.09667"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00403"},{"key":"ref12","article-title":"Robust contrastive language-image pretraining against data poisoning and backdoor attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang"},{"key":"ref13","article-title":"Better safe than sorry: Pre-training CLIP against targeted data poisoning and backdoor attacks","author":"Yang","year":"2023","journal-title":"arXiv:2310.05862"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00017"},{"key":"ref15","article-title":"BadCLIP: Dual-embedding guided backdoor attack on multimodal contrastive learning","author":"Liang","year":"2023","journal-title":"arXiv:2311.12075"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2025.3626950"},{"key":"ref17","first-page":"1","article-title":"Identifying vulnerabilities in the machine learning model supply chain","volume-title":"Proc. Neural Inf. Process. Symp. Workshop Mach. Learn. Secur. (MLSec)","author":"Gu"},{"key":"ref18","article-title":"Targeted backdoor attacks on deep learning systems using data poisoning","author":"Chen","year":"2017","journal-title":"arXiv:1712.05526"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_11"},{"key":"ref20","article-title":"WaNet\u2014Imperceptible warping-based backdoor attack","author":"Nguyen","year":"2021","journal-title":"arXiv:2102.10369"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01615"},{"key":"ref22","first-page":"39299","article-title":"Data poisoning attacks against multimodal encoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2024.103855"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00029"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00412"},{"key":"ref26","first-page":"1","article-title":"Neural polarizer: A lightweight and effective backdoor defense via purifying poisoned features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-8847-5_10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123618"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref31","article-title":"EVA-CLIP: Improved training techniques for CLIP at scale","author":"Sun","year":"2023","journal-title":"arXiv:2303.15389"},{"key":"ref32","article-title":"CosmoCLIP: Generalizing large vision-language models for astronomical imaging","author":"Imam","year":"2024","journal-title":"arXiv:2407.07315"},{"key":"ref33","article-title":"CEIA: CLIP-based event-image alignment for open-world event-based understanding","author":"Xu","year":"2024","journal-title":"arXiv:2407.06611"},{"key":"ref34","article-title":"Learning multiple layers of features from tiny images","volume-title":"Miscellaneous","author":"Krizhevsky","year":"2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref37","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. AISTATS","author":"Coates"},{"issue":"5","key":"ref38","first-page":"7","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS Workshop Deep Learn. Unsupervised Feature Learn.","volume":"2011","author":"Netzer","year":"2011"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref41","first-page":"3584","article-title":"Multimodal 3D object tracking in the wild: A state-of-the-art benchmark","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Hinterstoisser"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref43","article-title":"DeCLUTR: Deep contrastive learning for unsupervised textual representations","author":"Giorgi","year":"2020","journal-title":"arXiv:2006.03659"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/11221992.pdf?arnumber=11221992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:03:08Z","timestamp":1764183788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11221992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3626950","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}