{"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/deepfool-a-simple-and-accurate-method-to-fool","title":"DeepFool: a simple and accurate method to fool deep neural networks","arxiv_id":"1511.04599","date":"2015-11-14","proceeding":"CVPR 2016 6","authors":["Seyed-Mohsen Moosavi-Dezfooli","Alhussein Fawzi","Pascal Frossard"],"abstract":"State-of-the-art deep neural networks have achieved impressive results on\nmany image classification tasks. However, these same architectures have been\nshown to be unstable to small, well sought, perturbations of the images.\nDespite the importance of this phenomenon, no effective methods have been\nproposed to accurately compute the robustness of state-of-the-art deep\nclassifiers to such perturbations on large-scale datasets. In this paper, we\nfill this gap and propose the DeepFool algorithm to efficiently compute\nperturbations that fool deep networks, and thus reliably quantify the\nrobustness of these classifiers. Extensive experimental results show that our\napproach outperforms recent methods in the task of computing adversarial\nperturbations and making classifiers more robust.","url_abs":"http://arxiv.org/abs/1511.04599v3","url_pdf":"http://arxiv.org/pdf/1511.04599v3.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":"deepfool-a-simple-and-accurate-method-to-fool","repo_url":"https://github.com/LTS4/DeepFool","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deepfool-a-simple-and-accurate-method-to-fool","repo_url":"https://github.com/LTS4/SparseFool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deepfool-a-simple-and-accurate-method-to-fool","repo_url":"https://github.com/NetoPedro/Universal-Adversarial-Perturbations-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.04599","atlas_url":"https://app.syntology.ai/?focus=1511.04599","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}