An Artificial Immune System for Temporal Anomaly Detection Using Cell Activation Thresholds and Clonal Size Regulation with Homeostasis

This paper presents an Artificial Immune System (AIS) based on Grossman's Tunable Activation Threshold (TAT) for anomaly detection. We describe the immunological metaphor and the algorithm adopted for T-cells, emphasizing two important features: the temporal dynamic adjustment of T-cells clonal size and its associated homeostasis mechanism. We present some promising results obtained with artificially generated data sets, aiming to test the appropriateness of using TAT in dynamic changing environments, to distinguish new unseen patterns as part of what should be detected as normal or as anomalous.

[1]  Dejan Milutinovic,et al.  Immunological self-tolerance: lessons from mathematical modeling , 2005 .

[2]  Z. Grossman,et al.  Adaptive cellular interactions in the immune system: the tunable activation threshold and the significance of subthreshold responses. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Jonathan Timmis,et al.  Artificial Immune Systems: A New Computational Intelligence Approach , 2003 .

[4]  David A Rand,et al.  Dynamics of T cell activation threshold tuning. , 2004, Journal of theoretical biology.

[5]  João Pedro Pedroso,et al.  Simple Metaheuristics Using the Simplex Algorithm for Non-linear Programming , 2007, SLS.

[6]  Manuel Eduardo Correia,et al.  TAT-NIDS: An Immune-Based Anomaly Detection Architecture for Network Intrusion Detection , 2008, IWPACBB.

[7]  Julie Greensmith,et al.  Immune system approaches to intrusion detection – a review , 2004, Natural Computing.

[8]  Manuel Eduardo Correia,et al.  Towards an Immune-inspired Temporal Anomaly Detection Algorithm based on Tunable Activation Thresholds , 2009, BIOSIGNALS.

[9]  P. Matzinger.  The Danger Model: A Renewed Sense of Self , 2002, Science.

[10]  Claudia Eckert,et al.  On the appropriateness of negative selection defined over Hamming shape-space as a network intrusion detection system , 2005, 2005 IEEE Congress on Evolutionary Computation.

[11]  Z. Grossman,et al.  Tuning of activation thresholds explains flexibility in the selection and development of T cells in the thymus. , 1996, Proceedings of the National Academy of Sciences of the United States of America.