PROTECTION AGAINST COMPETITIVE ATTACKS ON MALICIOUS EXECUTABLE DETECTION METHODS USING MACHINE LEARNING ALGORITHMS
I.I. Marshev, E.V. Zhukovskiy, E.B. Aleksandrova
Annotation: Strength of malware detection methods based on machine learning algorithms has been analyzed. Adversarial attack for given methods has been developed. The method of robustness improvement of vulnerability detection methods has been proposed.
Keywords: malware detection, classification, machine learning, adversarial attack, neural network, static analysis.