An Improved Artificial Immune System Model

Abstract:

nspired by the theory of biological immune receptor editing/revision, an improved artificial immune system model is proposed. Different from generic model, the improved model does not need to set the detectors detection radius, but it gives the detector a certain degree of learning ability through receptor editing and receptor revision. This makes the detector has a capability to adjust the detection position and detection radius automatically. Experimental results show that the improved model achieves better detection performance than generic model.

• Periodical: Applied Mechanics and Materials (Volume 420)
• Pages: 311-317
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.420.311
• Online since: September 2013
• Authors: Gui Yang Li, Tao Guo
• Keywords: Artificial Immune System, Receptor Editing, Receptor Revision

References

[1] Timmis J., et al. Theoretical advances in artificial immune systems[J]. Theoretical Computer Science, 2008. 403(1): 11-32.

DOI: 10.1016/j.tcs.2008.02.011

[2] Hofmeyr S, Forrest S. Architecture for an artificial immune system[J]. Evolutionary Computation, 2000. 8(4): 443-473.

DOI: 10.1162/106365600568257

[3] Dasgupta D. Immunity-based intrusion detection system: A general framework[C]/ The 22nd National Information Systems Security Conf. 1999: 147-160.

[4] Harmer P, et al. H. An artificial immune system architecture for computer security applications[J]. IEEE Transaction on Evolutionary Computation, 2002. 6(3): 252-280.

[5] Kim J, Bentley P. Towards an artificial immune system for network intrusion detection: An investigation of dynamic clonal selection[C]/ Congress on Evolutionary Computation (CEC 2002). 2002: 1015-1020.

DOI: 10.1109/cec.2002.1004382

[6] Kim J, Bentley P. Immune memory and gene library evolution in the dynamic clonal selection algorithm[J]. Genetic Programming and Evolvable Machines, 2004. 5(4): 361-391.

DOI: 10.1023/b:genp.0000036019.81454.41

[7] Kim J, et al. Immune system approaches to intrusion detection–a review[J]. Natural computing, 2007. 6(4): 413-466.

[8] Kim J, Bentley P. An evaluation of negative selection in an artificial immune system for network intrusion detection[C]/ Proceedings of Genetic and Evolutionary Computation Conference (GECCO 2001). 2001: 1330–1337.

DOI: 10.1109/cec.2001.934333

[9] Timmis J. Artificial immune systems—today and tomorrow[J]. Natural Computing, 2007. 6(1): 1-18.

[10] Guiyang Li, Tao Guo, Receptor editing-inspired real negative selection algorithm[J], Computer Science, 2012. 39(8): 246-251.

[11] Wei Luo, Li Ma, Xiaoning Li, Receptor editing and revision in  peripheral T ceHs [J], Chinese Journal of Microbiology and Immunology, 2008. 3: 278-281.

[12] Stibor T, et al. A comparative study of real-valued negative selection to statistical anomaly detection techniques[C]/ Proceedings of Second International Conference on Artificial Immune System (ICARIS 2005). 2005: 262-272.

DOI: 10.1007/11536444_20