IRUS Total

On Bayesian new edge prediction and anomaly detection in computer networks

File Description SizeFormat 
new_edges.pdfAccepted version1.24 MBAdobe PDFView/Open
Title: On Bayesian new edge prediction and anomaly detection in computer networks
Authors: Metelli, S
Heard, N
Item Type: Journal Article
Abstract: Monitoring computer network traffic for anomalous behaviour presents an important security challenge. Arrivals of new edges in a network graph represent connections between a client and server pair not previously observed, and in rare cases these might suggest the presence of intruders or malicious implants. We propose a Bayesian model and anomaly detection method for simultaneously characterising existing network structure and modelling likely new edge formation. The method is demonstrated on real computer network authentication data and successfully identifies some machines which are known to be compromised.
Issue Date: 28-Nov-2019
Date of Acceptance: 12-Jul-2019
URI: http://hdl.handle.net/10044/1/71942
DOI: 10.1214/19-AOAS1286
ISSN: 1932-6157
Publisher: Institute of Mathematical Statistics
Start Page: 2586
End Page: 2610
Journal / Book Title: Annals of Applied Statistics
Volume: 13
Issue: 4
Copyright Statement: © Institute of Mathematical Statistics, 2019
Keywords: 0104 Statistics
Statistics & Probability
Publication Status: Published
Online Publication Date: 2019-11-28
Appears in Collections:Statistics
Faculty of Natural Sciences