Explaining Black-box Android Malware Detection

TitleExplaining Black-box Android Malware Detection
Publication TypeConference Paper
Year of Publication2018
AuthorsMelis, M, Maiorca, D, Biggio, B, Giacinto, G, Roli, F
Conference Name26th European Signal Processing Conference (EUSIPCO '18)
Date Published12/2018
Conference LocationRome, Italy
ISSN Number2076-1465
ISBN Number978-9-0827-9701-5
KeywordsApproximation algorithms, Detectors, Feature extraction, Machine Learning, Malware, Signal processing algorithms, support vector machines

Machine-learning models have been recently used for detecting malicious Android applications, reporting impressive performances on benchmark datasets, even when trained only on features statically extracted from the application, such as system calls and permissions. However, recent findings have highlighted the fragility of such in-vitro evaluations with benchmark datasets, showing that very few changes to the content of Android malware may suffice to evade detection. How can we thus trust that a malware detector performing well on benchmark data will continue to do so when deployed in an operating environment? To mitigate this issue, the most popular Android malware detectors use linear, explainable machine-learning models to easily identify the most influential features contributing to each decision. In this work, we generalize this approach to any black-box machine- learning model, by leveraging a gradient-based approach to identify the most influential local features. This enables using nonlinear models to potentially increase accuracy without sacrificing interpretability of decisions. Our approach also highlights the global characteristics learned by the model to discriminate between benign and malware applications. Finally, as shown by our empirical analysis on a popular Android malware detection task, it also helps identifying potential vulnerabilities of linear and nonlinear models against adversarial manipulations.

Citation Keymelis18-eusipco
melis18-eusipco-v3.pdf431.78 KB