EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detection. (arXiv:2110.03301v4 [cs.LG] UPDATED)

Over the last decade, researchers have extensively explored the
vulnerabilities of Android malware detectors to adversarial examples through
the development of evasion attacks; however, the practicality of these attacks
in real-world scenarios remains arguable. The majority of studies have assumed
attackers know the details of the target classifiers used for malware
detection, while in reality, malicious actors have limited access to the target
classifiers. This paper introduces EvadeDroid, a problem-space adversarial
attack designed to effectively evade black-box Android malware detectors …

adversarial android android malware arxiv attack attackers attacks box detection development evasion evasion attacks examples machine machine learning malware malware detection real researchers studies vulnerabilities world