{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:04Z","timestamp":1777890244701,"version":"3.51.4"},"reference-count":73,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00057","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"530-540","source":"Crossref","is-referenced-by-count":0,"title":["Boosting Generative Adversarial Transferability with Self-Supervised Vision Transformer Features"],"prefix":"10.1109","author":[{"given":"Shangbo","family":"Wu","sequence":"first","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-an","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruinan","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wencong","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dehua","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science and Technology, Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanzhang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref3","article-title":"Mixednuts: Training-free accuracy-robustness balance via nonlinearly mixed classifiers","volume":"2024","author":"Bai","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref4","article-title":"Beit: BERT pre-training of image transformers","author":"Bao","year":"2022","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML","author":"Chen","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"ref12","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Coates","year":"2011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML54575.2023.00024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref16","article-title":"Understanding self-supervised features for learning unsupervised instance segmentation","author":"Engstler","year":"2023","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01574"},{"key":"ref18","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","author":"Fu","year":"2023","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref20","article-title":"What do vision transformers learn? A visual exploration","author":"Ghiasi","year":"2022","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref22","article-title":"Bootstrap your own latent - A new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00483"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00723"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2741"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref32","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images. University of Toronto"},{"key":"ref33","article-title":"Adversarial machine learning at scale","author":"Kurakin","year":"2017","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94042-7_11"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"CoRR"},{"key":"ref38","article-title":"Boosting the transferability of adversarial attack on vision transformer with adaptive token tuning","author":"Ming","year":"2024","journal-title":"NeurIPS"},{"key":"ref39","article-title":"When adversarial training meets vision transformers: Recipes from training to architecture","author":"Mo","year":"2022","journal-title":"NeurIPS"},{"key":"ref40","first-page":"13950","article-title":"Learning transferable adversarial perturbations","author":"Nakka","year":"2021","journal-title":"NeurIPS"},{"key":"ref41","first-page":"12885","article-title":"Cross-domain transferability of adversarial perturbations","author":"Naseer","year":"2019","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref43","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref44","article-title":"What do self-supervised vision transformers learn?","author":"Park","year":"2023","journal-title":"ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00465"},{"issue":"8","key":"ref46","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref48","article-title":"Do adversarially robust imagenet models transfer better?","author":"Salman","year":"2020","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Bridging the gap to real-world objectcentric learning","author":"Seitzer","year":"2023","journal-title":"ICLR"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref51","article-title":"Revisiting adversarial training for imagenet: Architectures, training and generalization across threat models","author":"Deep Singh","year":"2023","journal-title":"NeurIPS"},{"key":"ref52","first-page":"8322","article-title":"Constructing unrestricted adversarial examples with generative models","author":"Song","year":"2018","journal-title":"NeurIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref55","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"ICML","author":"Tan","year":"2019"},{"key":"ref56","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","author":"Tolstikhin","year":"2021","journal-title":"NeurIPS"},{"key":"ref57","article-title":"Ensemble adversarial training: Attacks and defenses","author":"Tram\u00e8r","year":"2018","journal-title":"ICLR"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref59","article-title":"The caltech-ucsd birds-200\u20132011 dataset","volume-title":"Technical Report CNS-TR-2011-001","author":"Wah","year":"2011"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00754"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01967"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20169"},{"key":"ref63","article-title":"Fast is better than free: Revisiting adversarial training","author":"Wong","year":"2020","journal-title":"ICLR"},{"key":"ref64","first-page":"3905","article-title":"Generating adversarial examples with adversarial networks","author":"Xiao","year":"2018","journal-title":"IJCAI"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_3"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_42"},{"key":"ref69","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"Yosinski","year":"2014","journal-title":"NIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01575"},{"key":"ref71","article-title":"Beyond imagenet attack: Towards crafting adversarial examples for black-box domains","author":"Zhang","year":"2022","journal-title":"ICLR"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_28"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445789.pdf?arnumber=11445789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:38Z","timestamp":1777613558000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00057","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}