An Automatic Generation Alignment of Attack Signatures Based on Rule Matching Degree

Aiming at the problems of weak anti-noise ability and inaccurate signature generation of existing automatic attack signature generation methods proposing an algorithm based on rule matching degree in the context of the integrated Space-Earth integration network. Classify sequences based on rule matching degree (MDF), and construct a hierarchical guide tree according to the similarity between the two sequences. Then select the optimal alignment between two sequences according to the layers. Among them, the improved production rule sequence alignment algorithm (PRSA) is used to discover and retain comprehensible knowledge in the form of production rules. Fitness function is introduced and similarity measure function is modified to make the alignment between two sequences more reasonable. The experimental results show that this method has good anti-noise ability and the accuracy of attack feature extraction is higher.