{"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/non-negative-networks-against-adversarial","title":"Non-Negative Networks Against Adversarial Attacks","arxiv_id":"1806.06108","date":"2018-06-15","proceeding":null,"authors":["William Fleshman","Edward Raff","Jared Sylvester","Steven Forsyth","Mark McLean"],"abstract":"Adversarial attacks against neural networks are a problem of considerable\nimportance, for which effective defenses are not yet readily available. We make\nprogress toward this problem by showing that non-negative weight constraints\ncan be used to improve resistance in specific scenarios. In particular, we show\nthat they can provide an effective defense for binary classification problems\nwith asymmetric cost, such as malware or spam detection. We also show the\npotential for non-negativity to be helpful to non-binary problems by applying\nit to image classification.","url_abs":"http://arxiv.org/abs/1806.06108v2","url_pdf":"http://arxiv.org/pdf/1806.06108v2.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":"non-negative-networks-against-adversarial","repo_url":"https://github.com/endgameinc/malware_evasion_competition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"spam-detection","task_name":"Spam detection"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.06108","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}