Title
High-Speed Network Traffic Acquisition for Agent Systems
Abstract
This paper presents a design of high-speed network traffic acquisition subsystem suitable for agent-based intrusion detection systems. To match the performance requirements and to improve network traffic measurement, wire-speed data acquisition layer is based on hardware-accelerated probes, which provide real-time network traffic statistics. The network traffic is stored in collector servers and preprocessed data is then sent to detection agents that use heterogenous anomaly detection methods. These methods are correlated by means of trust and reputation models, and the conclusions regarding the maliciousness of the traffic is presented to the operator. Presented system is designed to improve the performance of agent-based intrusion detection systems and allow them to efficiently identify malicious traffic. The main contribution of presented system is its ability to aggregate real-time network-wide statistics from geographically dispersed probes. Traffic acquisition system is designed for deployment on high-speed backbone networks.
Year
DOI
Venue
2007
10.1109/IAT.2007.59
IAT
Keywords
Field
DocType
high-speed backbone network,heterogenous anomaly detection method,high-speed network traffic acquisition,network traffic measurement,agent systems,malicious traffic,presented system,network traffic,agent-based intrusion detection system,real-time network traffic statistic,traffic acquisition system,intrusion detection system,data acquisition,real time systems,real time,anomaly detection,hardware accelerator,multi agent systems,multiagent systems
Anomaly detection,Traffic generation model,Computer science,Floating car data,Computer network,Real-time computing,Network traffic measurement,Traffic shaping,Intrusion detection system,Network traffic control,Network traffic simulation
Conference
ISBN
Citations 
PageRank 
0-7695-3027-3
5
0.43
References 
Authors
6
4
Name
Order
Citations
PageRank
Pavel Celeda125127.91
Vojtech Krmicek2475.75
Martin Rehak325128.57
David Medvigy4162.32