{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:03:16Z","timestamp":1778799796695,"version":"3.51.4"},"reference-count":53,"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\/iccv51701.2025.01955","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21037-21047","source":"Crossref","is-referenced-by-count":1,"title":["Robustifying Zero-Shot Vision Language Models by Subspaces Alignment"],"prefix":"10.1109","author":[{"given":"Junhao","family":"Dong","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Koniusz","sequence":"additional","affiliation":[{"name":"Data61 CSIRO"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liaoyuan","family":"Feng","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Data61 CSIRO"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinghua","family":"Qu","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10125-w"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978322.63"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/591"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02215"},{"key":"ref7","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"International conference on machine learning","author":"Croce"},{"key":"ref8","article-title":"Robustbench: a standardized adversarial robustness benchmark","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","author":"Croce"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101896"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00882"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02364"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3266702"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290532"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3702638"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02686"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02696"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3379172"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709296"},{"key":"ref21","article-title":"Improving zeroshot adversarial robustness in vision-language models by closed-form alignment of adversarial path simplices","volume-title":"Forty-second International Conference on Machine Learning","author":"Dong"},{"key":"ref22","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations, ICLR","author":"Dosovitskiy"},{"key":"ref23","first-page":"2672","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.464"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390204"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02363"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref29","article-title":"Characterizing the decision boundary of deep neural networks","author":"Karimi","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.582"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107164"},{"key":"ref32","volume-title":"Higher-order occurrence pooling on midand low-level features: Visual concept detection","author":"Koniusz","year":"2013"},{"key":"ref33","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref38","article-title":"Understanding zero-shot adversarial robustness for large-scale models","volume-title":"The Eleventh International Conference on Learning Representations, ICLR","author":"Mao"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref40","volume-title":"Chatgpt [large language model]","year":"2024"},{"key":"ref41","first-page":"17258","article-title":"Robustness and accuracy could be reconcilable by (proper) definition","volume-title":"International Conference on Machine Learning","author":"Pang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref45","article-title":"Robust clip: Unsupervised adversarial fine-tuning of vision embeddings for robust large vision-language models","author":"Schlarmann","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"ref47","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2014","journal-title":"ICLR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02313"},{"key":"ref49","article-title":"Mitigating adversarial effects through randomization","volume-title":"International Conference on Learning Representations, ICLR","author":"Xie"},{"key":"ref50","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref52","article-title":"Clip in medical imaging: A comprehensive survey","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"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\/11444727.pdf?arnumber=11444727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:13Z","timestamp":1777612033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01955","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}