Evading control flow graph based GNN malware detectors via active opcode insertion method with maliciousness preserving

Evading control flow graph based GNN malware detectors via active opcode insertion method with maliciousness preserving

Abstract With the continuous advancement of machine learning, numerous malware detection methods that leverage this technology have emerged, presenting new challenges to the generation of adversarial malware. Existing function-preserving adversarial attacks fall short of effectively modifying portab...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Peng, Zehao Yu, Dandan Zhao, Zhiguo Ding, Jieshuai Yang, Bo Zhang, Jianming Han, Xuhong Zhang, Shouling Ji, Ming Zhong
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Subjects:
Malware Detection
Reinforcement Learning
Graph Neural Networks
Control Flow Graphs
Function-preserving
Online Access:https://doi.org/10.1038/s41598-025-92023-7
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://doi.org/10.1038/s41598-025-92023-7

Similar Items