Fuzzy Preference Approach for Computer Network Attack Detection

Irrepressible growth of complex interconnectedness of information systems besides its obvious benefits unfortunately brought up the questions of their vulnerability. Practically universal access to computers has enabled hackers and would-be terrorists to attack information systems and critical infrastructures worldwide. Fuzzy preference relation, based on fuzzy satisfaction function is applied to comparison of attack signatures. Fuzzy signatures (their gamma resolution sets) are combined by fuzzy operators. Therefore, qualitative, fuzzy decision fuzzy decision system is achieved. Different fuzzy set operators used in construction fuzzy satisfaction function, as also as different fuzzy preference relations have been tested. Proposed method provided smoother results that one obtained by traditional methods. Experiments demonstrated that final outcome dependence on correct determination of fuzzy values out of signature attacks, as also as on adequate choice of fuzzy set operator.