{"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/training-ensembles-to-detect-adversarial","title":"Training Ensembles to Detect Adversarial Examples","arxiv_id":"1712.04006","date":"2017-12-11","proceeding":null,"authors":["Alexander Bagnall","Razvan Bunescu","Gordon Stewart"],"abstract":"We propose a new ensemble method for detecting and classifying adversarial\nexamples generated by state-of-the-art attacks, including DeepFool and C&W. Our\nmethod works by training the members of an ensemble to have low classification\nerror on random benign examples while simultaneously minimizing agreement on\nexamples outside the training distribution. We evaluate on both MNIST and\nCIFAR-10, against oblivious and both white- and black-box adversaries.","url_abs":"http://arxiv.org/abs/1712.04006v1","url_pdf":"http://arxiv.org/pdf/1712.04006v1.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":"training-ensembles-to-detect-adversarial","repo_url":"https://github.com/bagnalla/ensemble_detect_adv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.04006","atlas_url":"https://app.syntology.ai/?focus=1712.04006","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}