Speaker: Patrick Rubin-Delanchy, Department of Statistics, University of Oxford
Title: Big Network Modeling and Anomaly Detection for Cyber-Security Applications
Abstract: Data arising in cyber-security applications often have a network, or `graph-like’, structure, and accurate statistical modelling of connectivity behaviour has important implications, for instance, for network intrusion detection. We present a linear algebraic approach to network modelling, which is massively scalable and also very general. In this approach, nodes are embedded in a finite dimensional latent space, where common statistical, signal-processing and machine-learning methodologies are then available. A central limit theorem provides asymptotic guarantees on the statistical accuracy of the embedding. We explore an intriguing connection between `disassortivity’, whereby nodes that are similar are relatively unlikely to connect, and space-time, as defined in special relativity. Mass testing for anomalous edges, correlations, and changepoints is then discussed. Results are illustrated on network flow data collected at Los Alamos National Laboratory.