Abstract: A fresh IDS evaluation method based on Bayesian theory was proposed, and a more perfect Intrusion Detection System Evaluation System was thus designed and constructed. Meanwhile, the four important indices to evaluate IDS, that is, function index, performance index, security index and user availabilityindex, were established. The specific quantitative analysis about some of the major indices was made, moreover, the process of intrusion and detection was simulated with probability tree. The results show that the presented method can find the optimal balance between the detection rate and false alarm rate of the system.

Key words: network security, intrusion detection, evaluation, Bayesian theory, probability tree, attack, test environment