关键词: 自律计算, 可信度评估, 入侵容忍, BP神经网络

Abstract: Intrusion tolerance has been a key technology of system survivability. Concerning the absence of self-adaptability on existent intrusion tolerance systems, an intrusion tolerance model based on autonomic computing was proposed. The reliability of the network connection was analyzed in real-time to generate the initial reliability by an autonomic feedback law, and the classification between suspicious information and confident information was guaranteed for implementing the tolerance on suspicious connections through the dynamic reliability optimization. The simulation results show that the intrusion tolerance model with autonomic feedback law can strengthen the self-adaptive performance of system.

Key words: autonomic computing, reliability evaluation, intrusion detection, Back Propagation (BP) neural network