Keystroke biometrics authentication system based on artificial neural network (ANN)

Abstract

In modern world of high technologies today, biometric types, now are becoming popular in various applications in which to build up password based authentication system. Traditional password approach is simply not practical since it can be forgoted and stollen. Keystroke biometrics is adopted in this thesis to extend and enhance the life of password technique for authentication solution. The system generates template of individual typing characteristics for typed password by considering three types of feature extraction; maximum force typing pressure, time latency, overall typing speed for improvement of the measurement accuracy and durability against intrusion to security system. An intelligent classification program based on Artificial Neural Network (ANN) is adopted. Learning Vector Quantization (LVQ) Network, Multilayer Feedforward Network (MFN), and Radial Basis Function (RBF) Network are used as classifier to verify ligitimate user and reject imposter attacks using the feature extraction module of individual traits. The performance of the proposed system is evaluated based on False Rejection Rate (FRR) and False Acceptance Rate (FAR). Experiments have been conducted to test the performance of overall keystroke biometrics system and the results obtained showed that the proposed systems can verify a user's identity with FRR and FAR; FRR is 2.25%, FAR close set and FAR open set are 0.167% and 2.45% respectively.