Semantic embeddings for program behaviour patterns

Alexander Chistyakov, Ekaterina Lobacheva, Arseny Kuznetsov, Alexey Romanenko

Feb 17, 2017 (modified: Mar 09, 2017) ICLR 2017 workshop submission readers: everyone
  • Abstract: In this paper, we propose a new feature extraction technique for program execution logs. First, we automatically extract complex patterns from a program's behaviour graph. Then, we embed these patterns into a continuous space by training an autoencoder. We evaluate the proposed features on a real-world malicious software detection task. We also find that the embedding space captures interpretable structures in the space of pattern parts.
  • TL;DR: We propose a novel method of graph based representation learning for program execution logs.
  • Conflicts: kaspersky.com, hse.ru, edu.hse.ru, cs.msu.ru
  • Keywords: Deep learning, Unsupervised Learning, Applications

Loading