Biological inspired anomaly detection based on danger theory

Intrusion detection systems play increasingly essential roles in modern society. With all various approaches used to Anomaly Detection, we investigate Artificial Immune Systems (AIS) to model anomaly detection. One new field of AIS is called Danger Theory. Since traditional Anomaly Detection Methods produce a large number of false alarms, AIS methods based on Danger Theory are suitable options for intrusion detection that can handle the above problem. So in this paper, we propose a novel method in danger theory field for anomaly detection and decrease the amount of system false alarms by using danger signals which are produced through a KNN classifier. Our experimental results show that this proposed method has low false alarm, by using the danger signals. Use of this danger signal that created by danger theory can improved our Artificial Immune Network and help us to achieve low false alarm in our results.