A recognition approach using multilayer perceptron and keyboard dynamics patterns

Multilayer perceptron (MLP) with one hidden layer is one of the most common forms of artificial neural networks ever utilized. A well-trained MLP with proper number of nodes in its hidden layer is demonstrated to have efficient and robust performance on patterns with high orders. In this paper in order to form an identification system, MLP is utilized as a classifier to distinguish keyboard dynamics patterns of several people. A variant number of neurons in the single hidden layer is investigated empirically to reach the optimum number. The optimum number of hidden layer neurons has been found to be 44 and relevant equal error rate (EER) equal to 0.95% has been reported. The false acceptance rate (FAR) and false reject rate (FRR) for this number of neuron has been empirically evaluated equal to 0.49% and 19.51% respectively.

[1]  Jiankun Hu,et al.  A k-Nearest Neighbor Approach for User Authentication through Biometric Keystroke Dynamics , 2008, 2008 IEEE International Conference on Communications.

[2]  Narasimhan Sundararajan,et al.  Radial Basis Function Neural Networks With Sequential Learning: Mran and Its Applications , 1999 .

[3]  Anil K. Jain,et al.  Keystroke dynamics for user authentication , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[4]  Xuan Wang,et al.  User authentication via keystroke dynamics based on difference subspace and slope correlation degree , 2012, Digit. Signal Process..

[5]  Frank Y. Shih,et al.  Image Processing and Pattern Recognition: Fundamentals and Techniques , 2010 .

[6]  Mark P. Wachowiak,et al.  Keystroke-based authentication by key press intervals as a complementary behavioral biometric , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[7]  S. S. Dlay,et al.  Performance of keystroke biometrics authentication system using artificial neural network (ANN) and distance classifier method , 2010, International Conference on Computer and Communication Engineering (ICCCE'10).

[8]  Ariën J. van der Wal.  Neuro-fuzzy controllers: Design and application: Jelena Godjevac , 1998, Robotics Auton. Syst..

[9]  Norman Shapiro,et al.  Authentication by Keystroke Timing: Some Preliminary Results , 1980 .

[10]  Yang Wang,et al.  A Model for User Authentication Based on Manner of Keystroke and Principal Component Analysis , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[11]  John R. Vacca,et al.  Biometric Technologies and Verification Systems , 2007 .

[12]  Karsten P. Ulland,et al.  Vii. References , 2022 .

[13]  Baptiste Hemery,et al.  Unconstrained keystroke dynamics authentication with shared secret , 2011, Comput. Secur..

[14]  Bojan Cukic,et al.  Keystroke Dynamics-Based Credential Hardening Systems , 2009, Handbook of Remote Biometrics.

[15]  Lakhmi C. Jain,et al.  Radial Basis Function Networks 2 , 2001 .

[16]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .

[17]  Kemal Bicakci,et al.  A second look at the performance of neural networks for keystroke dynamics using a publicly available dataset , 2012, Comput. Secur..

[18]  Elena Sapojnikova,et al.  ART-based fuzzy classifiers: ART fuzzy networks for automatic classification , 2004 .

[19]  Yves Chauvin,et al.  Backpropagation: theory, architectures, and applications , 1995 .

[20]  Lakhmi C. Jain,et al.  Radial Basis Function Networks 2: New Advances in Design , 2001 .