{"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/extending-defensive-distillation","title":"Extending Defensive Distillation","arxiv_id":"1705.05264","date":"2017-05-15","proceeding":null,"authors":["Nicolas Papernot","Patrick McDaniel"],"abstract":"Machine learning is vulnerable to adversarial examples: inputs carefully\nmodified to force misclassification. Designing defenses against such inputs\nremains largely an open problem. In this work, we revisit defensive\ndistillation---which is one of the mechanisms proposed to mitigate adversarial\nexamples---to address its limitations. We view our results not only as an\neffective way of addressing some of the recently discovered attacks but also as\nreinforcing the importance of improved training techniques.","url_abs":"http://arxiv.org/abs/1705.05264v1","url_pdf":"http://arxiv.org/pdf/1705.05264v1.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":"extending-defensive-distillation","repo_url":"https://github.com/SergioYF/defensive-distillation-papernot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.05264","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}