This paper proposes an integrated scheme to distinguish invasive events in optical fiber dual Mach–Zehnder Interferometry based perimeter security system. This algorithm combined empirical mode decomposition, kurtosis characteristics with radial basis function neural network, which can improve the recognition rate of event discrimination and increase the variety of intrusion events. Several experiments demonstrate that the proposed scheme can discriminate four common invasive events (climbing the fence, knocking the cable, cutting the fence, and waggling the fence) with an average recognition rate above 85.75%, which can satisfy actual application requirements.