Artficial Immune Systems and Their Applications
Artficial Immune Systems and Their Applications
Artificial Immune Systems: A New Computational Intelligence Paradigm
Artificial Immune Systems: A New Computational Intelligence Paradigm
Immunocomputing: Principles and Applications
Immunocomputing: Principles and Applications
Self-Nonself Discrimination in a Computer
SP '94 Proceedings of the 1994 IEEE Symposium on Security and Privacy
Data mining approaches for intrusion detection
SSYM'98 Proceedings of the 7th conference on USENIX Security Symposium - Volume 7
Immunological Computation: Theory and Applications
Immunological Computation: Theory and Applications
Immunocomputing for intelligent intrusion detection
IEEE Computational Intelligence Magazine
Decision support protocol for intrusion detection in VANETs
Proceedings of the third ACM international symposium on Design and analysis of intelligent vehicular networks and applications
Hi-index | 0.00 |
Most current anomaly based intrusion detection systems (IDS) use methods which rely on labeled training data. Such kind of data is expensive to produce and it is difficult to train such systems. Also these methods have difficulty in detecting new types of attacks and high rate of false positives. This paper offers an approach based on immune model and immunocomputing which allows training IDS without labeled attacks and shows a good performance on detecting new intrusions. Using immune model as the basic architecture for intrusion detection, we use immunocomputing techniques to increase efficiency of this model. The proposed IDS works in three modes: training mode, monitoring mode and adaptation mode. The last one is responsible for adaptation of IDS to the network traffic, which improves the performance of intrusion detection.