With the rapid growth of malware attacks, more antivirus developers consider deploying machine learning technologies into their productions. Researchers and developers published various machine learning-based detectors with high precision on malware detection in recent years. Although numerous machine learning-based malware detectors are available, they face various machine learning-targeted attacks, including evasion and adversarial attacks. This project explores how and why adversarial examples evade malware detectors, then proposes a randomised chaining method to defend against adversarial malware statically. This research is crucial for working towards combating the pertinent malware cybercrime.
@article{arxiv.2111.14037,
title = {Statically Detecting Adversarial Malware through Randomised Chaining},
author = {Matthew Crawford and Wei Wang and Ruoxi Sun and Minhui Xue},
journal= {arXiv preprint arXiv:2111.14037},
year = {2021}
}