An active distributed approach for cyber attack detection

With fast growing cyber activities everyday, cyber attack has become a critical issue over the last decade. A number of cyber attack detection algorithms have been developed and applied in this field of study with different levels of success. In this paper, a new distributed cyber attack detection algorithm based on the decision cost minimization strategy is introduced. The proposed algorithm employs sensor selection and active training techniques to reduce computational complexity for real time implementation without decreasing its effectiveness. The algorithm includes a data fusion rule to combine the decisions from distributed local binary classifiers using the decision cost function. KDD 1999 datasets are used to evaluate the proposed method. It is shown that the proposed detection system is a more flexible and suitable cyber attack detection solution for both known and unknown cyber attacks.