DAEMON: Dataset/Platform-Agnostic Explainable Malware Classification Using Multi-Stage Feature Mining

• Published in: IEEE access Vol. 9; pp. 78382 - 78399
• Main Authors: Korine, Ron, Hendler, Danny
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applications programs; Classification; Datasets; Feature extraction; Heuristic algorithms; Malware; Malware classification; malware families; Manuals; Mutation; server-side polymorphism; Smart phones; Static analysis; Tuning
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3082173

Numerous metamorphic and polymorphic malicious variants are generated automatically on a daily basis. In order to do that, malware vendors employ mutation engines that transform the code of a malicious program while retaining its functionality, aiming to evade signature-based detection. These automatic processes have greatly increased the number of malware variants, deeming their fully-manual analysis impossible. Malware classification is the task of determining to which family a new malicious variant belongs. Variants of the same malware family show similar behavioral patterns. Thus, classifying newly discovered malicious programs and applications helps assess the risks they pose. Moreover, malware classification facilitates determining which of the newly discovered variants should undergo manual analysis by a security expert, in order to determine whether they belong to a new family (e.g., one whose members exploit a zero-day vulnerability) or are simply the result of a concept drift within a known malicious family. This motivated intense research in recent years on devising high-accuracy automatic tools for malware classification. In this work, we present DAEMON-a novel dataset-agnostic malware classifier. A key property of DAEMON is that the type of features it uses and the manner in which they are mined facilitate understanding the distinctive behavior of malware families, making its classification decisions explainable . We've optimized DAEMON using a large-scale dataset of ×86 binaries, belonging to a mix of several malware families targeting computers running Windows. We then re-trained it and applied it, without any algorithmic change, feature re-engineering or parameter tuning, to two other large-scale datasets of malicious Android applications consisting of numerous malware families. DAEMON obtained highly accurate classification results on all datasets, establishing that it is not only dataset-agnostic but also platform-agnostic . We analyze DAEMON's classification models and provide numerous examples demonstrating how the features it uses facilitate explainability.