Abstract
Accuracy of anomaly-based intrusion detection greatly depends on features, the numerical values representing characteristics of network traffic. In order to increase accuracy, it is necessary to choose appropriate features that can correctly detect anomalous events. In this paper, we stress the fact that a specific kind of anomaly changes specific features. We propose a highly accurate and robust intrusion detection system using multiple features. Each feature is used for evaluating anomalous events independently by a statistical detection method. Through experiments, we investigate the accuracy of the proposed scheme.
Original language | English |
---|---|
Pages | 410-413 |
Number of pages | 4 |
Publication status | Published - 2007 |
Event | 3rd International Conference on Web Information Systems and Technologies, Webist 2007 - Barcelona, Spain Duration: 2007 Mar 3 → 2007 Mar 6 |
Other
Other | 3rd International Conference on Web Information Systems and Technologies, Webist 2007 |
---|---|
Country/Territory | Spain |
City | Barcelona |
Period | 07/3/3 → 07/3/6 |
Keywords
- Anomaly Detection
- Intrusion Detection System
- Multiple Network Features
- Principal Component Analysis
ASJC Scopus subject areas
- Computer Networks and Communications
- Hardware and Architecture
- Information Systems
- Electrical and Electronic Engineering