It is an established fact that malicious users in networks are able to mislead other users since the presence of herding behaviors, which will further amplify the hazards of these malicious behaviors. Due to the aforementioned scenarios in many practical applications, the study of decision fusion in the presence of such malicious users (often called Byzantines) is receiving increasing attention. In this paper, we propose an evolutionary game theoretical framework to model the human decision making process, which is based on the statistical signal processing framework. Specifically, we derive the analytical formulation of the evolutionary dynamics and the corresponding numerical evolutionary stable states, which can be utilized to infer the hazard of Byzantines on the network. Based on the above model and the Markov nature of the evolutionary dynamics, the fusion mechanism with maximum a posteriori estimation is proposed. Finally, simulation experiments are conducted to analyze the performance of the proposed human decision-making model and the effectiveness of the fusion mechanism under a variety of parameter settings.