Optimal Biometric-Based Continuous Authentication in Mobile Ad Hoc Networks

In mobile ad hoc networks (MANETs), continuous authentication is desirable so that a system can be monitored for the duration of the session to reduce the vulnerability. This paper presents an optimal biometric-based continuous authentication scheme in MANETs. We formulate the continuous authentication process as a partially observed Markov decision process, and use dynamic programming-based hidden Markov model scheduling algorithms to derive the optimal scheme for continuous authentication. Extensive simulations show the effectiveness of the proposed scheme.