ActDroid: An active learning framework for Android malware detection
This addresses the challenge of timely and cost-effective malware detection for Android users and developers, though it is incremental in applying active learning to this domain.
The paper tackled the problem of Android malware detection as a streaming data issue, using active online learning to reduce labeling costs and handle concept drift, achieving up to 96% accuracy with only 24% of training data labeled.
The growing popularity of Android requires malware detection systems that can keep up with the pace of new software being released. According to a recent study, a new piece of malware appears online every 12 seconds. To address this, we treat Android malware detection as a streaming data problem and explore the use of active online learning as a means of mitigating the problem of labelling applications in a timely and cost-effective manner. Our resulting framework achieves accuracies of up to 96\%, requires as little of 24\% of the training data to be labelled, and compensates for concept drift that occurs between the release and labelling of an application. We also consider the broader practicalities of online learning within Android malware detection, and systematically explore the trade-offs between using different static, dynamic and hybrid feature sets to classify malware.