Online Malware Detection with Variational Autoencoders

Abstrakt

This paper studies the application of variational autoencoders (VAEs) to online learning from malware detection data. To this end, it employs a large real-world dataset of anonymized highdimensional data collected during 375 consecutive weeks. Several VAEs were trained on selected subsets of this time series and subsequently tested on different subsets. For the assessment of their performance, the accuracy metric is complemented with the Wasserstein distance. In addition, the influence of different kinds of data normalization on the VAE performance has been investigated. Finally, the combinations of a VAE with two multi-layer perceptorns (MLPs) have been investigated, which has lead to the surprising result that the impact of such a combination on malware detection is positive for a simple and superficially optimized MLP, but negative for a complex and well optimized one.