{"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/learning-with-a-strong-adversary","title":"Learning with a Strong Adversary","arxiv_id":"1511.03034","date":"2015-11-10","proceeding":null,"authors":["Ruitong Huang","Bing Xu","Dale Schuurmans","Csaba Szepesvari"],"abstract":"The robustness of neural networks to intended perturbations has recently\nattracted significant attention. In this paper, we propose a new method,\n\\emph{learning with a strong adversary}, that learns robust classifiers from\nsupervised data. The proposed method takes finding adversarial examples as an\nintermediate step. A new and simple way of finding adversarial examples is\npresented and experimentally shown to be efficient. Experimental results\ndemonstrate that resulting learning method greatly improves the robustness of\nthe classification models produced.","url_abs":"http://arxiv.org/abs/1511.03034v6","url_pdf":"http://arxiv.org/pdf/1511.03034v6.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":"learning-with-a-strong-adversary","repo_url":"https://github.com/Armstring/LearningwithaStrongAdversary","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.03034","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}