{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:11:09Z","timestamp":1780517469401,"version":"3.54.1"},"reference-count":71,"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":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2025B0101120004"],"award-info":[{"award-number":["2025B0101120004"]}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2024A1515012006"],"award-info":[{"award-number":["2024A1515012006"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Open Foundation of Key Laboratory of Meteorological Software, China Meteorological Administration","award":["KLMS-OK-202503"],"award-info":[{"award-number":["KLMS-OK-202503"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3695647","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T22:56:47Z","timestamp":1780009007000},"page":"5657-5671","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Zero-Shot Adversarial Robustness of Vision\u2013Language Models With Training-Free Adaptive Feature Movement"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7979-9321","authenticated-orcid":false,"given":"Baoshun","family":"Tong","sequence":"first","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8057-6744","authenticated-orcid":false,"given":"Hanjiang","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0466-3763","authenticated-orcid":false,"given":"Yan","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1214-5384","authenticated-orcid":false,"given":"Jian","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yao"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02201"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3468884"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref9","article-title":"Pretrain like your inference: Masked tuning improves zero-shot composed image retrieval","author":"Chen","year":"2023","journal-title":"arXiv:2311.07622"},{"key":"ref10","article-title":"Understanding zero-shot adversarial robustness for large-scale models","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Mao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02313"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02304"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3211736"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00126"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3326398"},{"key":"ref16","article-title":"Diffusion models for adversarial purification","author":"Nie","year":"2022","journal-title":"arXiv:2205.07460"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02329"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","first-page":"25595","article-title":"Understanding robust overfitting of adversarial training and beyond","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yu"},{"key":"ref20","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5888"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01855"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00173"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3546840"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref28","article-title":"Test-time adaptation with clip reward for zero-shot generalization in vision-language models","volume-title":"Proc. ICLR","author":"Zhao"},{"key":"ref29","first-page":"6643","article-title":"Robust classification via a single diffusion model","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01304"},{"key":"ref31","first-page":"10440","article-title":"MarginGAN: Adversarial training in semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Dong"},{"key":"ref32","first-page":"3358","article-title":"Adversarial training for free!","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Shafahi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3184255"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290532"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104295"},{"key":"ref36","article-title":"A dive into SAM prior in image restoration","author":"Xiao","year":"2023","journal-title":"arXiv:2305.13620"},{"key":"ref37","article-title":"Can SAM boost video super-resolution?","author":"Lu","year":"2023","journal-title":"arXiv:2305.06524"},{"key":"ref38","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2167"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00387"},{"key":"ref42","first-page":"11838","article-title":"Theoretical evidence for adversarial robustness through randomization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Pinot"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2319"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780317"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/s1064827502419154"},{"key":"ref47","first-page":"5129","article-title":"Robustness may be at odds with accuracy","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Tsipras"},{"key":"ref48","first-page":"15147","article-title":"Understanding and mitigating the tradeoff between robustness and accuracy","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Raghunathan"},{"key":"ref49","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref50","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Coates"},{"key":"ref51","article-title":"Caltech-256 object category dataset","author":"Griffin","year":"7694"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref56","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.14585"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref64","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref65","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang"},{"key":"ref66","first-page":"9453","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Barbu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2355"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097245"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00078"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref71","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Croce"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11538359.pdf?arnumber=11538359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:45:24Z","timestamp":1780515924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11538359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3695647","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}