A Secure Authentication Method of Intelligent Terminals Based on Jensen-Shannon Divergence

To prevent information leakage and enhance the authentication security for intelligent terminals, this paper proposes an authentication method based on Jensen-Shannon divergence, which uses behavior characteristic distribution probability vector(BCDPV) obtained by normalizing and reconstructing the behavioral characteristics as an aided authentication beyond passwords. The security of the proposed method was evaluated and the results are presented using False Rejection Rate (FRR), False Acceptance Rate (FAR) and Equal Error Rate(ERR), which shows that the proposed method do the best job of identity authentication compared with other measurement method including the cosine, correlation euclidean and chebyshev, and has high security with the ERR under 3.179%. So the proposed authentication method is a feasible and secure method which balances convenience with efficiency and reduces performance overhead.