Litcius/Paper detail

When Malware is Packin' Heat; Limits of Machine Learning Classifiers Based on Static Analysis Features

Hojjat Aghakhani, Fabio Gritti, Francesco Mecca, Martina Lindorfer, Stefano Ortolani, Davide Balzarotti, Giovanni Vigna, Christopher Kruegel

2020130 citationsDOIOpen Access PDF

Abstract

Machine learning techniques are widely used in addition to signatures and heuristics to increase the detection rate of anti-malware software, as they automate the creation of detection models, making it possible to handle an ever-increasing number of new malware samples. In order to foil the analysis of anti-malware systems and evade detection, malware uses packing and other forms of obfuscation. However, few realize that benign applications use packing and obfuscation as well, to protect intellectual property and prevent license abuse.

Topics & Concepts

MalwareComputer scienceMachine learningObfuscationArtificial intelligenceFalse positive paradoxHeuristicsAdversarial machine learningSample (material)ExecutableDeep learningComputer securityOperating systemChromatographyChemistryAdvanced Malware Detection TechniquesNetwork Security and Intrusion DetectionAdversarial Robustness in Machine Learning
When Malware is Packin' Heat; Limits of Machine Learning Classifiers Based on Static Analysis Features | Litcius