MaxNet: Neural Network Architecture for Continuous Detection of Malicious Activity

Abstract

This paper addresses the detection of malware activity in a running application on the Android system. The detection is based on dynamic analysis and is formulated as a weakly supervised problem. We design an RNN sequential architecture able to continuously detect malicious activity using the proposed max-loss objective. The experiments were performed on a large industrial dataset consisting of 361,265 samples. The results demonstrate the performance of 96.2% true positive rate at 1.6% false positive rate which is superior to the state-of-the-art results. As part of this work, we release the dataset to the public.