Paper Info
Title
Multi-agent approach to network intrusion detection
Abstract
Our demo presents an agent-based intrusion detection system designed for deployment on high-speed backbone networks. The major contribution of the system is the integration of several anomaly detection techniques by means of collective trust modeling within a group of collaborative detection agents, each featuring a specific detection algorithm. The principal role of anomalies is to provide the input into the trust modeling stage of the detection, where each agent determines the flow trustfulness from aggregated anomalies. The aggregation is performed by extended trust models that model the trustfulness of generalized situated identities, represented by a set of observable features. The system is based on traffic statistics in NetFlow format acquired by dedicated hardware-accelerated network cards, and is able to perform a real-time surveillance of the gigabit networks.
Year
DOI
Venue
2008
10.5555/1402744.1402770
AAMAS (Demos)
Keywords
Field
DocType
collective trust modeling,anomaly detection technique,specific detection algorithm,extended trust model,collaborative detection agent,network intrusion detection,trust modeling stage,agent-based intrusion detection system,multi-agent approach,flow trustfulness,netflow format,aggregated anomaly,intrusion detection,trust
Situated,Anomaly detection,Gigabit,Data mining,Software deployment,NetFlow,Computer science,Anomaly-based intrusion detection system,Network interface controller,Intrusion detection system,Distributed computing
Conference
Citations 
PageRank 
References 
3
0.36
2
Authors
6
Name
Order
Citations
PageRank
Martin Rehak125128.57
Michal Pěchouček21134133.88
Pavel Celeda325127.91
Vojtech Krmicek4475.75
Martin Grill510110.79
Karel Bartos611012.60