International Journal of Engineering and Advanced Technology (IJEAT)
Intrusion detection system must be proficient of known and unknown vulnerabilities. In order to obtain superior accuracy an appropriate dataset should be there to detect the known and unknown attacks. In this paper new approach will be proposed which will utilize fuzzy if-then rules to detect known and unknown attacks i.e. sequential multilevel misuse along fuzzy if-then rules. In order to evaluate the performance of proposed algorithm and KDD'99 data set will be used. As fuzzy if-then rules comes up with overheads so overhead will be evaluated in this paper.