Cross Keyboard Keystroke Dynamics

Keystroke Dynamics is a biometric modality that is used for recognition of a person based on the typing rhythm on a keyboard. Keystroke Dynamics is a behavioural biometric and it is known that behaviour of a person can change when external conditions change. In most research the focus is on performance of the Keystroke Dynamics system under fixed conditions, while change of conditions has not received a lot of attention. In this paper we will specifically consider what happens if the user changes keyboards. We will focus on the performance of a system if a user enrolls using one keyboard, but then later authenticates using another type of keyboard. Our findings show that the performance of the Keystroke Dynamics system under such circumstances, in a small scale experiment, can lead to some deteriorated (of up to 8.10%) but also to a small gain (of up to 0.24 %). We found that the optimal solution is actually to create a reference based on a mixture of typing on both keyboards. Index Terms-Behavioural biometrics, keystroke dynamics, performance analysis, keyboard

[1]  L. O'Gorman,et al.  Comparing passwords, tokens, and biometrics for user authentication , 2003, Proceedings of the IEEE.

[2]  Roy A. Maxion,et al.  Comparing anomaly-detection algorithms for keystroke dynamics , 2009, 2009 IEEE/IFIP International Conference on Dependable Systems & Networks.

[3]  Christophe Rosenberger,et al.  Soft biometrics database: A benchmark for keystroke dynamics biometric systems , 2013, 2013 International Conference of the BIOSIG Special Interest Group (BIOSIG).

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

[5]  Patrick Bours,et al.  Performance of keystroke dynamics when allowing typing corrections , 2014, 2nd International Workshop on Biometrics and Forensics.

[6]  Stephanie Schuckers,et al.  Shared research dataset to support development of keystroke authentication , 2014, IEEE International Joint Conference on Biometrics.

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

[8]  Wm. Arthur Conklin,et al.  Password-based authentication: a system perspective , 2004, 37th Annual Hawaii International Conference on System Sciences, 2004. Proceedings of the.

[9]  Andrew Beng Jin Teoh,et al.  A Survey of Keystroke Dynamics Biometrics , 2013, TheScientificWorldJournal.

[10]  Julian Fiérrez,et al.  Keystroke dynamics recognition based on personal data: A comparative experimental evaluation implementing reproducible research , 2015, 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[11]  Baochang Zhang,et al.  Study on the BeiHang Keystroke Dynamics Database , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[12]  Roy A. Maxion,et al.  Free vs. transcribed text for keystroke-dynamics evaluations , 2012, LASER '12.

[13]  Noble Harter,et al.  Studies in the physiology and psychology of the telegraphic language , 1897 .

[14]  Claudia Picardi,et al.  User authentication through keystroke dynamics , 2002, TSEC.

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