Anomaly detection system with hole coverage optimization based on negative selection algorithm

Abstract

With the problem that a large number of undetectable holes existed in negative selection algorithm,an algorithm of directional generating holes’detectors using r -chunk matching rule with variable matching threshold based on hole-set and self-set was proposed.Improvement was made to negative selection algorithm that NSA with double layers detectors was proposed.This algorithm achieved a wider range of non-self space coverage with the precondition of ensuring fast detection speed by increasing the detection of holes.Simulation result shows that comparing with NSA using variable matching length of r -contiguous bits this algorithm can achieve higher non-self space coverage,especially better performance in hole-space coverage.

Keywords

• artificial immune systems;negative selection algorithm;hole;r-contiguous bits