{"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/ape-gan-adversarial-perturbation-elimination","title":"APE-GAN: Adversarial Perturbation Elimination with GAN","arxiv_id":"1707.05474","date":"2017-07-18","proceeding":null,"authors":["Shiwei Shen","Guoqing Jin","Ke Gao","Yongdong Zhang"],"abstract":"Although neural networks could achieve state-of-the-art performance while\nrecongnizing images, they often suffer a tremendous defeat from adversarial\nexamples--inputs generated by utilizing imperceptible but intentional\nperturbation to clean samples from the datasets. How to defense against\nadversarial examples is an important problem which is well worth researching.\nSo far, very few methods have provided a significant defense to adversarial\nexamples. In this paper, a novel idea is proposed and an effective framework\nbased Generative Adversarial Nets named APE-GAN is implemented to defense\nagainst the adversarial examples. The experimental results on three benchmark\ndatasets including MNIST, CIFAR10 and ImageNet indicate that APE-GAN is\neffective to resist adversarial examples generated from five attacks.","url_abs":"http://arxiv.org/abs/1707.05474v3","url_pdf":"http://arxiv.org/pdf/1707.05474v3.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":"ape-gan-adversarial-perturbation-elimination","repo_url":"https://github.com/shenqixiaojiang/APE-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"ape-gan-adversarial-perturbation-elimination","repo_url":"https://github.com/carlini/APE-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"ape-gan-adversarial-perturbation-elimination","repo_url":"https://github.com/owruby/ape-gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.05474","atlas_url":"https://app.syntology.ai/?focus=1707.05474","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}