论文信息 - Analysis of the acquisition process for keystroke dynamics

Analysis of the acquisition process for keystroke dynamics

In order to evaluate authentication methods for keystroke dynamics, it is necessary to create new datasets. We present in this paper an analysis study of the factors, involved during the acquisition process, which affect the performance of keystroke-based authentication systems. More generally speaking, we are looking for the optimal keystroke data acquisition scenario which may deeply affect the performance of such systems. Results show that (1) it is better to choose passwords based on short, simple and known words; and (2) during the acquisition process of a new keystroke dynamics dataset, there is no significant preference for displaying or telling to a user the text to type.

Christophe Rosenberger | Mohamad El-Abed | Romain Giot | Alexandre Ninassi

[1] Jugurta R. Montalvão Filho,et al. On the equalization of keystroke timing histograms , 2006, Pattern Recognit. Lett..

[2] Stergios B. Fotopoulos,et al. Introduction to Modern Nonparametric Statistics , 2004, Technometrics.

[3] Jeffrey D. Allen,et al. An analysis of pressure-based keystroke dynamics algorithms , 2010 .

[4] Jean-Yves Ramel,et al. User Classification for Keystroke Dynamics Authentication , 2007, ICB.

[5] J. J. Higgins. Introduction to Modern Nonparametric Statistics , 2003 .

[6] Christophe Rosenberger,et al. GREYC keystroke: A benchmark for keystroke dynamics biometric systems , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[7] Roy A. Maxion,et al. Should Security Researchers Experiment More and Draw More Inferences? , 2011, CSET.

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