Attention-Based Self-Supervised Feature Learning for Security Data
This addresses the need for automated feature learning in cyber-security to reduce errors and reliance on domain expertise, though it appears incremental as it builds on existing self-supervised and attention-based approaches.
The paper tackled the problem of manual feature construction in cyber-security machine learning by designing a self-supervised sequence-to-sequence model with attention to learn embeddings, resulting in better performance in anomaly detection compared to baseline methods on two real-world datasets.
While applications of machine learning in cyber-security have grown rapidly, most models use manually constructed features. This manual approach is error-prone and requires domain expertise. In this paper, we design a self-supervised sequence-to-sequence model with attention to learn an embedding for data routinely used in cyber-security applications. The method is validated on two real world public data sets. The learned features are used in an anomaly detection model and perform better than learned features from baseline methods.