{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:08:04Z","timestamp":1789668484726,"version":"4.0.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>Adversarial training is effective on balanced datasets, but its robustness degrades under long-tailed class distributions, where tail classes suffer high robust error and unstable decision boundaries. We propose \\emph{Manifold-Constrained Adversarial Training (MCAT)}, a unified framework that enforces the semantic validity of adversarial examples by penalizing deviations from class-conditional manifolds in feature space, while promoting balanced geometric separation across classes via an ETF-inspired regularization. We provide theoretical results that link geometric separation to lower bounds on adversarially robust margins, and show that manifold-constrained adversarial risk upper-bounds robust risk on high-density semantic regions. Extensive experiments on standard long-tailed benchmarks demonstrate consistent improvements in overall, balanced, and tail-class adversarial robustness. The codes and appendix are available on https:\/\/github.com\/yneversky\/MCAT.<\/jats:p>","DOI":"10.24963\/ijcai.2026\/565","type":"proceedings-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:01:13Z","timestamp":1789596073000},"page":"5074-5082","source":"Crossref","is-referenced-by-count":0,"title":["Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment"],"prefix":"10.24963","author":[{"given":"Guanmeng","family":"Xian","sequence":"first","affiliation":[{"name":"Sichuan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Yang","sequence":"additional","affiliation":[{"name":"Sichuan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-Fifth International Joint Conference on Artificial Intelligence {IJCAI-26}","theme":"Artificial Intelligence","location":"Bremen, Germany","acronym":"IJCAI-2026","number":"35","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2025,8,16]]},"end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:35:30Z","timestamp":1789666530000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2026\/565"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2026\/565","relation":{},"subject":[],"published":{"date-parts":[[2026,9]]}}}