Semantic embeddings for program behavior patterns
This addresses the problem of improving detection capabilities for malicious software in cybersecurity, but it appears incremental as it builds on existing embedding and autoencoder methods.
The paper tackled the problem of feature extraction from program execution logs by proposing a new technique that embeds complex behavior patterns into a continuous space using an autoencoder, and it was evaluated on a real-world malicious software detection task, though no concrete numbers were provided for the results.
In this paper, we propose a new feature extraction technique for program execution logs. First, we automatically extract complex patterns from a program's behavior 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.