{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:39:52Z","timestamp":1773801592492,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Adversarial patch attacks inject localized perturbations into images to mislead deep vision models. These attacks can be physically deployed, posing serious risks to real-world applications. In this paper, we propose CertMask, a certifiably robust defense that constructs a provably sufficient set of binary masks to neutralize patch effects with strong theoretical guarantees. While the state-of-the-art approach (PatchCleanser) requires two rounds of masking and incurs O(n^2) inference cost, CertMask performs only a single round of masking with O(n) time complexity, where n is the cardinality of the mask set to cover an input image. Our proposed mask set is computed using a mathematically rigorous coverage strategy that ensures each possible patch location is covered at least k times, providing both efficiency and robustness. We offer a theoretical analysis of the coverage condition and prove its sufficiency for certification. Experiments on ImageNet, ImageNette, and CIFAR-10 show that CertMask improves certified robust accuracy by up to +13.4% over PatchCleanser, while maintaining clean accuracy nearly identical to the vanilla model.<\/jats:p>","DOI":"10.1609\/aaai.v40i10.37716","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:44:59Z","timestamp":1773791099000},"page":"7735-7743","source":"Crossref","is-referenced-by-count":0,"title":["CertMask: Certifiable Defense Against Adversarial Patches via Theoretically Optimal Mask Coverage"],"prefix":"10.1609","volume":"40","author":[{"given":"Xuntao","family":"Lyu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Chi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdullah Al","family":"Arafat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Von der Br\u00fcggen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian-Jia","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhishan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37716\/41678","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37716\/41678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:44:59Z","timestamp":1773791099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i10.37716","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}