Artificial Immune System for Anomaly Detection

One significant feature of the theory immunology is the ability to adapt to changing environments and dynamically learning continuously. Based on this idea, artificial immune systems (AISs) provide an ideal inspiration for computer security in general and intrusion detection systems (IDSs) in particular. A hybrid immune learning algorithm is presented in this paper with the aim of combining the advantages of real-valued negative selection algorithm (RNSA) and a classification algorithm. The basic idea is to use the RNSA algorithm to generate non-self samples. Then, apply a classification algorithm to find a characteristic function of the self (or non-self). This algorithm allows the application of a supervised learning technique even when samples from only one class (normal) are available.