On copulas-based classification method for intrusion detection

Abstract

The intent of this paper is to develop a nonparametric classification method using copulas to estimate the conditional probability for an element to be a member of a connected class while taking into account the dependence of the attributes of this element. This technique is suitable for different types of data, even those whose probability distribution is not Gaussian. To improve the effectiveness of the method, we apply it to a problem of network intrusion detection where prior classes are topologically connected.