{"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/black-box-attacks-against-rnn-based-malware","title":"Black-Box Attacks against RNN based Malware Detection Algorithms","arxiv_id":"1705.08131","date":"2017-05-23","proceeding":null,"authors":["Weiwei Hu","Ying Tan"],"abstract":"Recent researches have shown that machine learning based malware detection\nalgorithms are very vulnerable under the attacks of adversarial examples. These\nworks mainly focused on the detection algorithms which use features with fixed\ndimension, while some researchers have begun to use recurrent neural networks\n(RNN) to detect malware based on sequential API features. This paper proposes a\nnovel algorithm to generate sequential adversarial examples, which are used to\nattack a RNN based malware detection system. It is usually hard for malicious\nattackers to know the exact structures and weights of the victim RNN. A\nsubstitute RNN is trained to approximate the victim RNN. Then we propose a\ngenerative RNN to output sequential adversarial examples from the original\nsequential malware inputs. Experimental results showed that RNN based malware\ndetection algorithms fail to detect most of the generated malicious adversarial\nexamples, which means the proposed model is able to effectively bypass the\ndetection algorithms.","url_abs":"http://arxiv.org/abs/1705.08131v1","url_pdf":"http://arxiv.org/pdf/1705.08131v1.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":"black-box-attacks-against-rnn-based-malware","repo_url":"https://github.com/MindSpore-scientific/code-3/tree/main/Black-Box-Attacks-against","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"malware-detection","task_name":"Malware Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1705.08131","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}