{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:35Z","timestamp":1778048315853,"version":"3.51.4"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00042","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"350-359","source":"Crossref","is-referenced-by-count":0,"title":["Cluster-Guided Adversarial Perturbations for Robust Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Seongyun","family":"Seo","sequence":"first","affiliation":[{"name":"Korea University,School of Cybersecurity,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungmin","family":"Han","sequence":"additional","affiliation":[{"name":"Korea University,School of Cybersecurity,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeonghyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,School of Cybersecurity,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangkyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,School of Cybersecurity,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","author":"Arora","year":"2019","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref3","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref5","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref6","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Coates"},{"key":"ref7","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","author":"Croce","year":"2020","journal-title":"ICML"},{"key":"ref8","article-title":"Robustbench: A standardized adversarial robustness benchmark","author":"Croce","year":"2021","journal-title":"NeurIPS Datasets and Benchmarks Track"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","first-page":"21480","article-title":"When does contrastive learning preserve adversarial robustness from pretraining to finetuning?","author":"Fan","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018","journal-title":"ICLR"},{"key":"ref12","first-page":"21271","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref14","first-page":"5000","article-title":"Provable guarantees for self-supervised deep learning with spectral contrastive loss","author":"HaoChen","year":"2021","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v050.i10"},{"key":"ref18","first-page":"35533","article-title":"Non-linguistic supervision for contrastive learning of sentence embeddings","author":"Jian","year":"2022","journal-title":"NeurIPS"},{"key":"ref19","first-page":"16199","article-title":"Robust pre-training by adversarial contrastive learning","author":"Jiang","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","first-page":"2983","article-title":"Adversarial self-supervised contrastive learning","author":"Kim","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Learning multiple layers of features from tiny images","volume-title":"Technical report","author":"Krizhevsky","year":"2009"},{"key":"ref22","article-title":"Fine-tuning can distort pre-trained features and underperform out-of-distribution","author":"Kumar","year":"2022","journal-title":"ICLR"},{"key":"ref23","first-page":"309","article-title":"Predicting what you already know helps: Provable self-supervised learning","author":"Lee","year":"2021","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Rethinking the effect of data augmentation in adversarial contrastive learning","author":"Luo","year":"2023","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref26","article-title":"On detecting adversarial perturbations","author":"Metzen","year":"2017","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref30","first-page":"3407","article-title":"Demystifying contrastive self-supervised learning: Invariances, augmentations and dataset biases","author":"Purushwalkam","year":"2020","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Fixing data augmentation to improve adversarial robustness","author":"Rebuffi","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref33","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2014","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref35","article-title":"Contrastive learning, multi-view redundancy, and linear models","author":"Tosh","year":"2020"},{"key":"ref36","article-title":"Robustness may be at odds with accuracy","author":"Tsipras","year":"2019","journal-title":"ICLR"},{"key":"ref37","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","author":"Wang","year":"2020","journal-title":"ICML"},{"key":"ref38","article-title":"Towards frequency-based explanation for robust cnn","author":"Wang","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00059"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23198"},{"key":"ref41","first-page":"75798","article-title":"Efficient adversarial contrastive learning via robustness-aware coreset selection","author":"Xu","year":"2023","journal-title":"NeurIPS"},{"key":"ref42","first-page":"16783","article-title":"Enhancing adversarial contrastive learning via adversarial invariant regularization","author":"Xu","year":"2023","journal-title":"NeurIPS"},{"key":"ref43","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021","journal-title":"ICML"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_42"},{"key":"ref45","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","author":"Zhang","year":"2019","journal-title":"ICML"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492389.pdf?arnumber=11492389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:21Z","timestamp":1778046981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492389\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00042","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}