{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T23:15:24Z","timestamp":1763507724061},"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":[[2019,8]]},"abstract":"<jats:p>Machine learning techniques, especially deep neural networks (DNNs), have been widely adopted in various applications. However, DNNs are recently found to be vulnerable against adversarial examples, i.e., maliciously perturbed inputs that can mislead the models to make arbitrary prediction errors.\nEmpirical defenses have been studied, but many of them can be adaptively attacked again. \nProvable defenses provide provable error bound of DNNs, while such bound so far is far from satisfaction. \nTo address this issue, in this paper, we present our approach named Robustra for effectively improving the provable error bound of DNNs. \nWe leverage the adversarial space of a reference model as the feasible region to solve the min-max game between the attackers and defenders. \nWe solve its dual problem by linearly approximating the attackers' best strategy and utilizing the monotonicity of the slack variables introduced by the reference model.\nThe evaluation results show that our approach can provide significantly better provable adversarial error bounds on MNIST and CIFAR10 datasets, compared to the state-of-the-art results. In particular, bounded by L^infty, with epsilon = 0.1, on MNIST we reduce the error bound from 2.74% to 2.09%; with epsilon = 0.3, we reduce the error bound from 24.19% to 16.91%.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/654","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"4711-4717","source":"Crossref","is-referenced-by-count":8,"title":["Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space"],"prefix":"10.24963","author":[{"given":"Linyi","family":"Li","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexuan","family":"Zhong","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2019","name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","start":{"date-parts":[[2019,8,10]]},"theme":"Artificial Intelligence","location":"Macao, China","end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:50:50Z","timestamp":1564300250000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/654"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/654","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}