{"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/combating-adversarial-attacks-using-sparse","title":"Combating Adversarial Attacks Using Sparse Representations","arxiv_id":"1803.03880","date":"2018-03-11","proceeding":null,"authors":["Soorya Gopalakrishnan","Zhinus Marzi","Upamanyu Madhow","Ramtin Pedarsani"],"abstract":"It is by now well-known that small adversarial perturbations can induce\nclassification errors in deep neural networks (DNNs). In this paper, we make\nthe case that sparse representations of the input data are a crucial tool for\ncombating such attacks. For linear classifiers, we show that a sparsifying\nfront end is provably effective against $\\ell_{\\infty}$-bounded attacks,\nreducing output distortion due to the attack by a factor of roughly $K / N$\nwhere $N$ is the data dimension and $K$ is the sparsity level. We then extend\nthis concept to DNNs, showing that a \"locally linear\" model can be used to\ndevelop a theoretical foundation for crafting attacks and defenses.\nExperimental results for the MNIST dataset show the efficacy of the proposed\nsparsifying front end.","url_abs":"http://arxiv.org/abs/1803.03880v3","url_pdf":"http://arxiv.org/pdf/1803.03880v3.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":"combating-adversarial-attacks-using-sparse","repo_url":"https://github.com/soorya19/sparsity-based-defenses","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"combating-adversarial-attacks-using-sparse","repo_url":"https://github.com/ZhinusMarzi/Adversarial-attack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"combating-adversarial-attacks-using-sparse","repo_url":"https://github.com/ZhinusMarzi/Sparsity-based-defenses-against-adversarial-attacks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.03880","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}