The T-detectors maturation algorithm based on match range model

ABSTRACT

Negative selection algorithm is used to generate detector for change detection, anomaly detection. But it can not be adapted to the change of self data because the match threshold must be set at first. In this paper, inspired from the maturation of T-cells, a match range model is proposed. Base on the model, a novel algorithm composed of positive selection and negative selection is proposed to generate T-detectors and the match threshold is not needed. Genetic algorithm is used to evolve the detectors with self-adapted match range. The proposed algorithm is tested by simulation experiment for anomaly detection and compared with the negative selection algorithm. The results show that the proposed algorithm is more effective than the negative selection algorithm and match range is self-adapted.

REFERENCES

• 1: Stephanie Forrest , Alan S. Perelson , Lawrence Allen , Rajesh Cherukuri, Self-Nonself Discrimination in a Computer, Proceedings of the 1994 IEEE Symposium on Security and Privacy, p.202, May 16-18, 1994
• 2: Dasgupta D., Forrest S., Novelty Detection in Time Series Data using Ideas from Immunology. In Proceedings of The International Conference on Intelligent Systems, 1999.
• 3: Steven Andrew Hofmeyr , Stephanie Forrest, An immunological model of distributed detection and its application to computer security, 1999
• 4: Fabio A. González , Dipankar Dasgupta, Anomaly Detection Using Real-Valued Negative Selection, Genetic Programming and Evolvable Machines, v.4 n.4, p.383-403, December 2003 [doi>10.1023/A:1026195112518]
• 5: Fabio Augusto Gonzalez , Dipankar Dasgupta, A study of artificial immune systems applied to anomaly detection, 2003

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Analogies

General Terms:
Algorithms, Security, Theory

Keywords:
T-cells maturation, match range, negative selection