{"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/out-distribution-training-confers-robustness","title":"Out-distribution training confers robustness to deep neural networks","arxiv_id":"1802.07124","date":"2018-02-20","proceeding":null,"authors":["Mahdieh Abbasi","Christian Gagné"],"abstract":"The easiness at which adversarial instances can be generated in deep neural\nnetworks raises some fundamental questions on their functioning and concerns on\ntheir use in critical systems. In this paper, we draw a connection between\nover-generalization and adversaries: a possible cause of adversaries lies in\nmodels designed to make decisions all over the input space, leading to\ninappropriate high-confidence decisions in parts of the input space not\nrepresented in the training set. We empirically show an augmented neural\nnetwork, which is not trained on any types of adversaries, can increase the\nrobustness by detecting black-box one-step adversaries, i.e. assimilated to\nout-distribution samples, and making generation of white-box one-step\nadversaries harder.","url_abs":"http://arxiv.org/abs/1802.07124v3","url_pdf":"http://arxiv.org/pdf/1802.07124v3.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":"out-distribution-training-confers-robustness","repo_url":"https://github.com/mahdaneh/Out-distribution-learning_FSvisulization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}