Classification of IDS Alerts with Data Mining Techniques

Intrusion detection systems (IDSs) have become a widely used measure for security, but we still have a problem on those systems results which includes many irrelevant alerts, so we will propose a data mining based method for classification to distinguish serious alerts and irrelevant one with the performance of 99.9 % in comparison with the other recent data mining methods which have reached the performance of 97%. Also we create a list of alerts sorted by alert’s importance to minimize the human interventions. Keyword: Intrusion Detection, Data Mining, Frequent Pattern, Frequent Itemset, support