MHIDCA: Multi Level Hybrid Intrusion Detection and Continuous Authentication for MANET Security

Mobile ad-hoc networks have attracted a great deal of attentions over the past few years. Considering their applications, the security issue has a great significance in them. Security scheme utilization that includes prevention and detection has the worth of consideration. In this paper, a method is presented that includes a multi-level security scheme to identify intrusion by sensors and authenticates using biosensors. Optimizing authentication and intrusion detection combination, we formulate the problem as a partially observable distributed stochastic system. In order to reduce the computation time, the parallel forward algorithm of Hidden Markov Model has been used. Due to the possibility of misdetection of the sensor and in order to increase the accuracy of observations, more than one sensor is selected in every step, the observations obtained from the sensors are combined for more accurate identification, and the system decides about the security status based on combined observations of the sensors. Bayesian theory has been used in sensors evidence fusion brought by increased accuracy and network security, which will be observed in the simulations. The use of this theory causes the increase of accuracy and security on networks.

MHIDCA: Multi Level Hybrid Intrusion Detection and Continuous Authentication for MANET Security Keywords:

Security , Mobile ad-hoc Networks , Authentication , Intrusion Detection , Hidden Markov Model