Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approach

no code implementations • 4 Feb 2024 • Brian Etter, James Lee Hu, Mohammedreza Ebrahimi, Weifeng Li, Xin Li, Hsinchun Chen

Adversarial Malware Generation (AMG), the gen- eration of adversarial malware variants to strengthen Deep Learning (DL)-based malware detectors has emerged as a crucial tool in the development of proactive cyberdefense.

Malware Detection reinforcement-learning +1

Multi-view Representation Learning from Malware to Defend Against Adversarial Variants

no code implementations • 25 Oct 2022 • James Lee Hu, MohammadReza Ebrahimi, Weifeng Li, Xin Li, Hsinchun Chen

This provides an opportunity for the defenders (i. e., malware detectors) to detect the adversarial variants by utilizing more than one view of a malware file (e. g., source code view in addition to the binary view).

Adversarial Robustness MULTI-VIEW LEARNING +1

Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach

no code implementations • 3 Dec 2021 • James Lee Hu, MohammadReza Ebrahimi, Hsinchun Chen

Given that most malware detectors enforce a query limit, this could result in generating non-realistic adversarial examples that are likely to be detected in practice due to lack of stealth.

Language Modelling