Anomaly Detection in IP Networks

Description | Publications | People | Collaborators | Funding

Description

Statistical techniques for detecting anomalous events can be an invaluable tool for the operators of large IP networks. In this project, we explore the use of statistical techniques, such as wavelets, Principal Component Analysis, and Kalman-based filters, in automatically detecting and diagnosing anomalies. The research draws on analyzing large volumes of traffic and routing data collected from many vantage points.

Publications

People

Collaborators

Funding

The research on BGP anomaly detection is part of the project on
"Incrementally Deployable Secure Interdomain Routing" funded by HSARPA. The research on detecting traffic anomalies is partially funded by Thomson Technology Paris Lab.