{"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/transferable-sparse-adversarial-attack","title":"Transferable Sparse Adversarial Attack","arxiv_id":"2105.14727","date":"2021-05-31","proceeding":"CVPR 2022 1","authors":["Ziwen He","Wei Wang","Jing Dong","Tieniu Tan"],"abstract":"Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the $\\ell_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a high attack success rate, prior sparse attack methods achieve a low transferability under the black-box protocol due to overfitting the target model. Therefore, we introduce a generator architecture to alleviate the overfitting issue and thus efficiently craft transferable sparse adversarial examples. Specifically, the generator decouples the sparse perturbation into amplitude and position components. We carefully design a random quantization operator to optimize these two components jointly in an end-to-end way. The experiment shows that our method has improved the transferability by a large margin under a similar sparsity setting compared with state-of-the-art methods. Moreover, our method achieves superior inference speed, 700$\\times$ faster than other optimization-based methods. The code is available at https://github.com/shaguopohuaizhe/TSAA.","url_abs":"https://arxiv.org/abs/2105.14727v1","url_pdf":"https://arxiv.org/pdf/2105.14727v1.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":"transferable-sparse-adversarial-attack","repo_url":"https://github.com/NiCE-X/TSAA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"transferable-sparse-adversarial-attack","repo_url":"https://github.com/shaguopohuaizhe/TSAA","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}