{"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/constrained-gradient-descent-a-powerful-and","title":"Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks","arxiv_id":"2112.14232","date":"2021-12-28","proceeding":null,"authors":["Weiran Lin","Keane Lucas","Lujo Bauer","Michael K. Reiter","Mahmood Sharif"],"abstract":"We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks better align with the attacker's goal: (1) tricking a model to assign higher probability to the target class than to any other class, while (2) staying within an $\\epsilon$-distance of the attacked input. First, we demonstrate a loss function that explicitly encodes (1) and show that Auto-PGD finds more attacks with it. Second, we propose a new attack method, Constrained Gradient Descent (CGD), using a refinement of our loss function that captures both (1) and (2). CGD seeks to satisfy both attacker objectives -- misclassification and bounded $\\ell_{p}$-norm -- in a principled manner, as part of the optimization, instead of via ad hoc post-processing techniques (e.g., projection or clipping). We show that CGD is more successful on CIFAR10 (0.9--4.2%) and ImageNet (8.6--13.6%) than state-of-the-art attacks while consuming less time (11.4--18.8%). Statistical tests confirm that our attack outperforms others against leading defenses on different datasets and values of $\\epsilon$.","url_abs":"https://arxiv.org/abs/2112.14232v2","url_pdf":"https://arxiv.org/pdf/2112.14232v2.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":"constrained-gradient-descent-a-powerful-and","repo_url":"https://github.com/linweiran/CGD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"hoc","method_name":"HOC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.14232","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}