Distributed Detection Filter for Intrusion Detection

Detection Filter Design for distributed intrusion detection using spectral assignment

This submission simulates the implementation of a spectral approach to isolate multiple malicious agents in a dynamic network of cooperating agents. The problem addressed is the problem of simultaneously identifying m intruders in a network consisting of n cooperative agents. The simulation identifies attacks through a distributed scheme that uses detection filters. It has been shown that the problem of identifying multiple attackers can be formulated as a spectral assignment problem and that the filter gains can be obtained through a carefully constructed linear system of equations, which we implement here. Please see Nazari et al "Distributed Detection Filter Design for Intruder Identification" American Control Conference 2016 for more information.