Security term in mobile ad hoc networks has several aspects because of the special specification of these networks. In this paper a distributed architecture was proposed in which each node performed intrusion detection based on its own and its neighbors’ data. Fuzzy-neural interface was used that is the composition of learning ability of neural network and fuzzy Ratiocination of fuzzy system as our architecture engine. Our scrutiny showed that fuzzy-neural interface had a good ability for separating normal data from abnormal. The ability of proposed architecture was evaluated in accuracy and overhead case.