Combining Conjunctive Rule Extraction with Diffusion Maps for Network Intrusion Detection

Network security and intrusion detection are important in the modern world where communication happens via information networks. Traditional signature-based intrusion detection methods cannot find previously unknown attacks. On the other hand, algorithms used for anomaly detection often have black box qualities that are difficult to understand for people who are not algorithm experts. Rule extraction methods create interpretable rule sets that act as classifiers. They have mostly been combined with already labeled data sets. This paper aims to combine unsupervised anomaly detection with rule extraction techniques to create an online anomaly detection framework. Unsupervised anomaly detection uses diffusion maps and clustering for labeling an unknown data set. Rule sets are created using conjunctive rule extraction algorithm. This research suggests that the combination of machine learning methods and rule extraction is a feasible way to implement network intrusion detection that is meaningful to network administrators.