Fusion approach on keystroke dynamics to enhance the performance of password authentication

We propose in this paper a novel technique to enhance the performance of password authentication using various fusion approach on keystroke dynamics. To strengthen the password authentication, introduce additional layer of keystroke patterns used for authentication. Firstly, extract keystroke features from our database. Then calculate mean and standard deviation of keystroke features to form the template. Hybrid model based on combination of Gaussian probability density function (GPDF) and Support Vector Machine (SVM) will convert test features into scores. Lastly, four fusion rules are applied to improve the final result by fusing the GPDF and SVM scores. Best result with equal error rate of 1.612% is obtained with our database.