AI RESEARCH
Explainability-Guided Adversarial Attacks on Transformer-Based Malware Detectors Using Control Flow Graphs
arXiv CS.LG
•
ArXi:2604.03843v1 Announce Type: cross Transformer-based malware detection systems operating on graph modalities such as control flow graphs (CFGs) achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial evasion attacks remains underexplored.