Network Security White Papers
HIDE: A Hierarchical Network Intrusion Detection System Using Statistical Preprocessing and Neural Network Classification
Overview This paper introduces the Hierarchical Intrusion DEtection (HIDE) system, which detects network-based attacks as anomalies using statistical preprocessing and neural network classification. The paper describe the system architecture and the statistical preprocessing technique and components. Five different types of neural network classifiers are tested those are Perceptron, BackPropagation (BP), Perceptron-BackOropagation-hybrid (PBH), Fuzzy ARTMAP, and Radial-based Function. The results indicate that BP and PBH provide more efficient classification for the data than the alternatives. The authors also stress-tested the entire system, which showed that HIDE can reliably detect UDP flooding attacks with attack intensity as low as five to ten percent of background traffic.
| Publisher | City College of The City University of New York | File Format | |
|---|---|---|---|
| Date Published | June 2001 | ||
| Format | White Papers | ||
| Topics | |||
-
Did you find this white paper useful? 3 out of 5 users found this white paper useful
White Paper RSS
Download
Register
