{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/robustifying-ell-infty-adversarial-training","title":"Robustifying $\\ell_\\infty$ Adversarial Training to the Union of Perturbation Models","arxiv_id":"2105.14710","date":"2021-05-31","proceeding":"NeurIPS 2021 12","authors":["Ameya D. Patil","Michael Tuttle","Alexander G. Schwing","Naresh R. Shanbhag"],"abstract":"Classical adversarial training (AT) frameworks are designed to achieve high adversarial accuracy against a single attack type, typically $\\ell_\\infty$ norm-bounded perturbations. Recent extensions in AT have focused on defending against the union of multiple perturbations but this benefit is obtained at the expense of a significant (up to $10\\times$) increase in training complexity over single-attack $\\ell_\\infty$ AT. In this work, we expand the capabilities of widely popular single-attack $\\ell_\\infty$ AT frameworks to provide robustness to the union of ($\\ell_\\infty, \\ell_2, \\ell_1$) perturbations while preserving their training efficiency. Our technique, referred to as Shaped Noise Augmented Processing (SNAP), exploits a well-established byproduct of single-attack AT frameworks -- the reduction in the curvature of the decision boundary of networks. SNAP prepends a given deep net with a shaped noise augmentation layer whose distribution is learned along with network parameters using any standard single-attack AT. As a result, SNAP enhances adversarial accuracy of ResNet-18 on CIFAR-10 against the union of ($\\ell_\\infty, \\ell_2, \\ell_1$) perturbations by 14%-to-20% for four state-of-the-art (SOTA) single-attack $\\ell_\\infty$ AT frameworks, and, for the first time, establishes a benchmark for ResNet-50 and ResNet-101 on ImageNet.","url_abs":"https://arxiv.org/abs/2105.14710v3","url_pdf":"https://arxiv.org/pdf/2105.14710v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robustifying-ell-infty-adversarial-training","repo_url":"https://github.com/adpatil2/SNAP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.14710","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}