{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T02:13:30Z","timestamp":1778552010304,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["62576030"],"award-info":[{"award-number":["62576030"]}],"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":["62572040"],"award-info":[{"award-number":["62572040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3659598","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:03:08Z","timestamp":1769806988000},"page":"6615-6627","source":"Crossref","is-referenced-by-count":0,"title":["NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0991-7109","authenticated-orcid":false,"given":"Jiaming","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9531-6662","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2099-4973","authenticated-orcid":false,"given":"Xingjun","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0571-8156","authenticated-orcid":false,"given":"Lingyu","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Applications “R. Caccioppoli”, University of Naples Federico II, Via Cintia, Monte S. Angelo, Naples, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0699-3205","authenticated-orcid":false,"given":"Jitao","family":"Sang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_4"},{"key":"ref4","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0102"},{"key":"ref6","article-title":"Adversarial prompt distillation for vision-language models","author":"Luo","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref9","first-page":"5019","article-title":"Adversarially robust generalization requires more data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schmidt"},{"key":"ref10","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01093"},{"key":"ref12","article-title":"Understanding zero-shot adversarial robustness for large-scale models","author":"Mao","year":"2023","journal-title":"The Eleventh Int. Conf. Learn. Representations"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref14","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref19","article-title":"Improving adversarial robustness requires revisiting misclassified examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02788"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01854"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01413"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25452"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref28","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref34","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00196"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"ref38","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"},{"key":"ref39","article-title":"A frustratingly simple yet highly effective attack baseline: Over 90% success rate against the strong black-box models of GPT-4.5\/4o\/o1","author":"Li","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206626"},{"key":"ref41","first-page":"16805","article-title":"Diffusion models for adversarial purification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nie"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11368741.pdf?arnumber=11368741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:54:01Z","timestamp":1778550841000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11368741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":41,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3659598","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}