Hanoi, Vietnam 25-03-2018
Nowadays, hackers use different types of attacks for getting the valuable information. Many intrusion detection techniques, methods and algorithms help to detect these attacks. In this paper, a rule evolution approach using Surrogate model on Tree Adjoining Grammar Guided Genetic Programming (SuTAG3P) for generating new rules. A testing dataset proposed by DARPA is used to evaluate these new rules. The proof of concept implementation shows that a rule generated by SuTAG3P has a low false positive rate (FPR), a low false negative rate and a high true positive rate of detecting attacks.
Index Terms— attack detection; intrusion detection system; tag3p, genetic programming, surrogate model.