{"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/zk-gandef-a-gan-based-zero-knowledge","title":"ZK-GanDef: A GAN based Zero Knowledge Adversarial Training Defense for Neural Networks","arxiv_id":"1904.08516","date":"2019-04-17","proceeding":null,"authors":["Guanxiong Liu","Issa Khalil","Abdallah Khreishah"],"abstract":"Neural Network classifiers have been used successfully in a wide range of\napplications. However, their underlying assumption of attack free environment\nhas been defied by adversarial examples. Researchers tried to develop defenses;\nhowever, existing approaches are still far from providing effective solutions\nto this evolving problem. In this paper, we design a generative adversarial net\n(GAN) based zero knowledge adversarial training defense, dubbed ZK-GanDef,\nwhich does not consume adversarial examples during training. Therefore,\nZK-GanDef is not only efficient in training but also adaptive to new\nadversarial examples. This advantage comes at the cost of small degradation in\ntest accuracy compared to full knowledge approaches. Our experiments show that\nZK-GanDef enhances test accuracy on adversarial examples by up-to 49.17%\ncompared to zero knowledge approaches. More importantly, its test accuracy is\nclose to that of the state-of-the-art full knowledge approaches (maximum\ndegradation of 8.46%), while taking much less training time.","url_abs":"http://arxiv.org/abs/1904.08516v1","url_pdf":"http://arxiv.org/pdf/1904.08516v1.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":"zk-gandef-a-gan-based-zero-knowledge","repo_url":"https://github.com/GuanxiongLiu/DSN-ZK-GanDef","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}