K-Median Based Network Attack Detection

Provided by: Bioinfo Publications
Topic: Networking
Format: PDF
The clustered detection of network attacks represents an extremely challenging goal. Current methods rely on either very specialized signatures of previously seen attacks, or on expensive and difficult to produce labeled traffic datasets for profiling and training. In this paper, the authors present a completely clustered approach to detect attacks, without relying on signatures, labeled traffic, or training. The method uses robust clustering techniques to detect anomalous traffic flows, sequentially captured in a temporal sliding-window basis.

Find By Topic