{"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/stochastic-sparse-adversarial-attacks","title":"Stochastic sparse adversarial attacks","arxiv_id":"2011.12423","date":"2020-11-24","proceeding":null,"authors":["Manon Césaire","Lucas Schott","Hatem Hajri","Sylvain Lamprier","Patrick Gallinari"],"abstract":"This paper introduces stochastic sparse adversarial attacks (SSAA), standing as simple, fast and purely noise-based targeted and untargeted attacks of neural network classifiers (NNC). SSAA offer new examples of sparse (or $L_0$) attacks for which only few methods have been proposed previously. These attacks are devised by exploiting a small-time expansion idea widely used for Markov processes. Experiments on small and large datasets (CIFAR-10 and ImageNet) illustrate several advantages of SSAA in comparison with the-state-of-the-art methods. For instance, in the untargeted case, our method called Voting Folded Gaussian Attack (VFGA) scales efficiently to ImageNet and achieves a significantly lower $L_0$ score than SparseFool (up to $\\frac{2}{5}$) while being faster. Moreover, VFGA achieves better $L_0$ scores on ImageNet than Sparse-RS when both attacks are fully successful on a large number of samples.","url_abs":"https://arxiv.org/abs/2011.12423v4","url_pdf":"https://arxiv.org/pdf/2011.12423v4.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":"stochastic-sparse-adversarial-attacks","repo_url":"https://github.com/SSAA3/stochastic-sparse-adv-attacks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"stochastic-sparse-adversarial-attacks","repo_url":"https://github.com/hhajri/stochastic-sparse-adv-attacks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"stochastic-sparse-adversarial-attacks","repo_url":"https://github.com/jeromerony/adversarial-library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.12423","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}