Acoustical keystroke analysis for user identification and authentication

This article describes a new algorithm of calibrated user authentication using acoustical monitoring of keyboard when typing the pre-defined word. The HMM (Hidden Markov Models) with MFCC (Mel-frequency cepstral coefficients) features were used in the setup. In authentication task a low EER (Equal Error Rate) was achieved between 9.4% and 14.8% using a calibration setup and 3 sessions training. For identification part the accuracy of 99.33% was achieved, when testing 25% of realizations (randomly selected from 100 recordings) identifying between 50 users/models. Calibration was done using one user recording to calibrate the microphone and keyboard table setup when enrolling his model. Genuine and impostor tests were realized for 50 volunteers typing 100 words each in 4 sessions.

[1]  Jozef Juhár,et al.  Feature selection for acoustic events detection , 2013, Multimedia Tools and Applications.

[2]  Arun Ross,et al.  Investigating the Discriminative Power of Keystroke Sound , 2015, IEEE Transactions on Information Forensics and Security.

[3]  Jozef Juhar,et al.  Distance-based dialog acts labeling , 2015, 2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom).

[4]  Rakesh Agrawal,et al.  Keyboard acoustic emanations , 2004, IEEE Symposium on Security and Privacy, 2004. Proceedings. 2004.

[5]  Hiroshi Dozono,et al.  Adaptive authentication system for behavior biometrics using supervised pareto self organizing maps , 2008 .

[6]  Patrick Bours.  Continuous keystroke dynamics: A different perspective towards biometric evaluation , 2012, Inf. Secur. Tech. Rep..

[7]  Martin Lojka,et al.  Comparison of Different Feature Types for Acoustic Event Detection System , 2013, MCSS.

[8]  M. Akila,et al.  Biometric personal authentication using keystroke dynamics: A review , 2011, Appl. Soft Comput..

[9]  Xiaoming Liu,et al.  On Continuous User Authentication via Typing Behavior , 2014, IEEE Transactions on Image Processing.

[10]  Patrick Bours,et al.  Static Audio Keystroke Dynamics , 2015, MCSS.

[11]  Jozef Juhar,et al.  A Study of Acoustic Features for Emotional Speaker Recognition in I-Vector Representation , 2015 .

[12]  Feng Zhou,et al.  Keyboard acoustic emanations revisited , 2005, CCS '05.

[13]  Hiroshi Dozono,et al.  Comparison of the Adaptive Authentication Systems for Behavior Biometrics using the Variations of Self Organizing Maps , 2008 .

[14]  Steve Young,et al.  The HTK book version 3.4 , 2006 .

[15]  Arun Ross,et al.  Biometric authentication via keystroke sound , 2013, 2013 International Conference on Biometrics (ICB).

[16]  Damon L. Woodard,et al.  Biometric Authentication and Identification using Keystroke Dynamics: A Survey , 2012 .

[17]  Jozef Juhar,et al.  Acoustical User Identification Based on MFCC Analysis of Keystrokes , 2015 .