featured

Proactive insider threat detection through graph learning and psychological context
by Oliver Brdiczka, Julia Liu, Jianqiang Shen, Richard Chow, Eugene Bart and Nic Ducheneaut

While there are a number of existing tools that can accurately identify known attacks, these are reactively as opposed to proactively enforced. Furthermore, the tools may be eluded by previously unseen adversarial behaviors. This paper proposes an approach that combines Structural Anomaly Detection (graph analysis, dynamic tracking, and machine learning on large-scale social and information networks) and Psychological Profiling (constructed dynamically from behavioral patterns of individuals) to detect anomalies and prevent insider threats.

more