{"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/defending-against-adversarial-attacks-by","title":"Defending Against Adversarial Attacks by Leveraging an Entire GAN","arxiv_id":"1805.10652","date":"2018-05-27","proceeding":null,"authors":["Gokula Krishnan Santhanam","Paulina Grnarova"],"abstract":"Recent work has shown that state-of-the-art models are highly vulnerable to\nadversarial perturbations of the input. We propose cowboy, an approach to\ndetecting and defending against adversarial attacks by using both the\ndiscriminator and generator of a GAN trained on the same dataset. We show that\nthe discriminator consistently scores the adversarial samples lower than the\nreal samples across multiple attacks and datasets. We provide empirical\nevidence that adversarial samples lie outside of the data manifold learned by\nthe GAN. Based on this, we propose a cleaning method which uses both the\ndiscriminator and generator of the GAN to project the samples back onto the\ndata manifold. This cleaning procedure is independent of the classifier and\ntype of attack and thus can be deployed in existing systems.","url_abs":"http://arxiv.org/abs/1805.10652v1","url_pdf":"http://arxiv.org/pdf/1805.10652v1.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":"defending-against-adversarial-attacks-by","repo_url":"https://github.com/mnswdhw/DefenseGAN-and-Cowboy-Defense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}