{"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/patch-wise-attack-for-fooling-deep-neural","title":"Patch-wise Attack for Fooling Deep Neural Network","arxiv_id":"2007.06765","date":"2020-07-14","proceeding":"ECCV 2020 8","authors":["Lianli Gao","Qilong Zhang","Jingkuan Song","Xianglong Liu","Heng Tao Shen"],"abstract":"By adding human-imperceptible noise to clean images, the resultant adversarial examples can fool other unknown models. Features of a pixel extracted by deep neural networks (DNNs) are influenced by its surrounding regions, and different DNNs generally focus on different discriminative regions in recognition. Motivated by this, we propose a patch-wise iterative algorithm -- a black-box attack towards mainstream normally trained and defense models, which differs from the existing attack methods manipulating pixel-wise noise. In this way, without sacrificing the performance of white-box attack, our adversarial examples can have strong transferability. Specifically, we introduce an amplification factor to the step size in each iteration, and one pixel's overall gradient overflowing the $\\epsilon$-constraint is properly assigned to its surrounding regions by a project kernel. Our method can be generally integrated to any gradient-based attack methods. Compared with the current state-of-the-art attacks, we significantly improve the success rate by 9.2\\% for defense models and 3.7\\% for normally trained models on average. Our code is available at \\url{https://github.com/qilong-zhang/Patch-wise-iterative-attack}","url_abs":"https://arxiv.org/abs/2007.06765v3","url_pdf":"https://arxiv.org/pdf/2007.06765v3.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":"patch-wise-attack-for-fooling-deep-neural","repo_url":"https://github.com/qilong-zhang/Patch-wise-iterative-attack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"patch-wise-attack-for-fooling-deep-neural","repo_url":"https://github.com/Trustworthy-AI-Group/TransferAttack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"patch-wise-attack-for-fooling-deep-neural","repo_url":"https://github.com/qilong-zhang/Targeted_Patch-wise-plusplus_iterative_attack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"patch-wise-attack-for-fooling-deep-neural","repo_url":"https://github.com/ylhz/tf_to_pytorch_model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.06765","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}