Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approach
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917582157643776 |
|---|---|
| author | Etter, Brian Hu, James Lee Ebrahimi, Mohammedreza Li, Weifeng Li, Xin Chen, Hsinchun |
| author_facet | Etter, Brian Hu, James Lee Ebrahimi, Mohammedreza Li, Weifeng Li, Xin Chen, Hsinchun |
| contents | Adversarial Malware Generation (AMG), the generation of adversarial malware variants to strengthen Deep Learning (DL)-based malware detectors has emerged as a crucial tool in the development of proactive cyberdefense. However, the majority of extant works offer subtle perturbations or additions to executable files and do not explore full-file obfuscation. In this study, we show that an open-source encryption tool coupled with a Reinforcement Learning (RL) framework can successfully obfuscate malware to evade state-of-the-art malware detection engines and outperform techniques that use advanced modification methods. Our results show that the proposed method improves the evasion rate from 27%-49% compared to widely-used state-of-the-art reinforcement learning-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02600 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approach Etter, Brian Hu, James Lee Ebrahimi, Mohammedreza Li, Weifeng Li, Xin Chen, Hsinchun Cryptography and Security Artificial Intelligence Machine Learning Adversarial Malware Generation (AMG), the generation of adversarial malware variants to strengthen Deep Learning (DL)-based malware detectors has emerged as a crucial tool in the development of proactive cyberdefense. However, the majority of extant works offer subtle perturbations or additions to executable files and do not explore full-file obfuscation. In this study, we show that an open-source encryption tool coupled with a Reinforcement Learning (RL) framework can successfully obfuscate malware to evade state-of-the-art malware detection engines and outperform techniques that use advanced modification methods. Our results show that the proposed method improves the evasion rate from 27%-49% compared to widely-used state-of-the-art reinforcement learning-based methods. |
| title | Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approach |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.02600 |