{"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/generating-adversarial-malware-examples-for","title":"Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN","arxiv_id":"1702.05983","date":"2017-02-20","proceeding":null,"authors":["Weiwei Hu","Ying Tan"],"abstract":"Machine learning has been used to detect new malware in recent years, while\nmalware authors have strong motivation to attack such algorithms. Malware\nauthors usually have no access to the detailed structures and parameters of the\nmachine learning models used by malware detection systems, and therefore they\ncan only perform black-box attacks. This paper proposes a generative\nadversarial network (GAN) based algorithm named MalGAN to generate adversarial\nmalware examples, which are able to bypass black-box machine learning based\ndetection models. MalGAN uses a substitute detector to fit the black-box\nmalware detection system. A generative network is trained to minimize the\ngenerated adversarial examples' malicious probabilities predicted by the\nsubstitute detector. The superiority of MalGAN over traditional gradient based\nadversarial example generation algorithms is that MalGAN is able to decrease\nthe detection rate to nearly zero and make the retraining based defensive\nmethod against adversarial examples hard to work.","url_abs":"http://arxiv.org/abs/1702.05983v1","url_pdf":"http://arxiv.org/pdf/1702.05983v1.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":"generating-adversarial-malware-examples-for","repo_url":"https://github.com/CyberForce/Pesidious","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"generating-adversarial-malware-examples-for","repo_url":"https://github.com/Vi45en/Pesidious","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generating-adversarial-malware-examples-for","repo_url":"https://github.com/yanminglai/Malware-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"generating-adversarial-malware-examples-for","repo_url":"https://github.com/yortyj/Exploiting-GANs-for-Phun-and-Profit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"malware-detection","task_name":"Malware Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.05983","atlas_url":"https://app.syntology.ai/?focus=1702.05983","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}