An Intrusion Alarm System Based on Fuzzy Reasoning Machine
Jiyao An, WU Ronghui, Renfa Li, Cheng Xu · 2007
A new intrusion alarm system is presented in this paper which is skillfully combined with fuzzy reasoning and neural network technology. In order to overcome the difficulty of specifying the membership function of rules depending on experiences of experts in multi-dimensional space, fuzzy reasoning machine network model is introduced to carry through proper nonlinear division of input/output characteristics of complex system. The new system architecture adopts the network processor to collect and analyze the data in the low layer of network, and a test prototype system is established. For an example of network traffic character by network worm, we realize abnormal network behavior, which is caused by the change of network traffic, can be detected in time and accurately.