Abstract—Artificial Immune System (AIS) is inspired by biological immune system and provides novel ways to solve complex problems including fault detection, optimization and anomaly detection. Artificial Negative Selection is one the most important branches in AIS that discriminates normal and anomalous samples based on natural immune system self/non-self discrimination mechanism. In this paper a new schema of detector generation approach for negative selection is introduced. Negative selection is typically applied to anomaly detection problems, which can be considered as a type of pattern classification problem and is typically employed as an intrusion detection technique. This new approach, hybrids ideas from Artificial Immune Negative Selection algorithms and Restricted Coulomb Energy neural networks that are specific design of hyper sphere classifiers. While generated detectors have variable radius in real-valued space. The algorithm is tested using real-world datasets, including NSL-KDD99. The experiments in this paper showed the algorithm can tightly control the number of generated detectors.
Index Terms—Detector generation, RCE network, negative selection.
This work was supported in part by the Iran Telecommunication Research Center (ITRC) under Grant 8971/500. Authors are with the Computer Department of Alzahra university, Tehran, Iran (e-mail: Tahereh.Pourhabibi@student.alzahra.ac.ir; r.azmi@alzahra.ac.ir).
Cite:T. Pourhabibi and R. Azmi, "Anomaly Based IDS Using Variable Size Detector Generation in AIS: A Hybrid Approach," International Journal of Machine Learning and Computing vol.2, no. 3, pp. 200-203, 2012.