{"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/adversarial-examples-attacks-and-defenses-for","title":"Adversarial Examples: Attacks and Defenses for Deep Learning","arxiv_id":"1712.07107","date":"2017-12-19","proceeding":null,"authors":["Xiaoyong Yuan","Pan He","Qile Zhu","Xiaolin Li"],"abstract":"With rapid progress and significant successes in a wide spectrum of\napplications, deep learning is being applied in many safety-critical\nenvironments. However, deep neural networks have been recently found vulnerable\nto well-designed input samples, called adversarial examples. Adversarial\nexamples are imperceptible to human but can easily fool deep neural networks in\nthe testing/deploying stage. The vulnerability to adversarial examples becomes\none of the major risks for applying deep neural networks in safety-critical\nenvironments. Therefore, attacks and defenses on adversarial examples draw\ngreat attention. In this paper, we review recent findings on adversarial\nexamples for deep neural networks, summarize the methods for generating\nadversarial examples, and propose a taxonomy of these methods. Under the\ntaxonomy, applications for adversarial examples are investigated. We further\nelaborate on countermeasures for adversarial examples and explore the\nchallenges and the potential solutions.","url_abs":"http://arxiv.org/abs/1712.07107v3","url_pdf":"http://arxiv.org/pdf/1712.07107v3.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":"adversarial-examples-attacks-and-defenses-for","repo_url":"https://github.com/revbucket/mister_ed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.07107","atlas_url":"https://app.syntology.ai/?focus=1712.07107","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}