Reliable and Interpretable Android Malware Detection at Scale

Machine learning approaches have shown impressive performance in Android malware detection. Yet, most if not all of these approaches face tradeoffs between accuracy, interpretability, and scalability. Approaches based on simple features are interpretable but miss complex behaviors. At the same time, approaches that capture holistic application patterns obscure the exact code responsible for malicious activity. In this paper, we outline our vision for an accurate, scalable, and interpretable method-level malware detection. The core idea behind our approach is to filter out non-discriminative application parts before analyzing the remaining, applicationspecific behaviors at the fine level of granularity. We further discuss the key challenges that must be addressed to effectively implement our proposed approach and provide suggestions for future directions.