Lamarckian Evolution of Neural Networks Applied to Keystroke Dynamics

The pace of computing and communications development has contributed to an increased data exposure and, consequently, to the rise of an issue known as identity theft. By applying user profiling, which analyzes the user behavior in order to perform a continuous authentication, protection of digital identities can be enhanced. Among the possible features to be analyzed, this paper focuses on keystroke dynamics, something that cannot be easily stolen. As keystroke dynamics involves dealing with noisy data, it was chosen a neural network to perform the pattern recognition task. However, traditional neural network training algorithms are bound to get trapped in local minimum, reducing the learning ability. This work draws a comparison between backpropagation and two hybrid approaches based on evolutionary training, for the task of keystroke dynamics. Differently from most evolutionary algorithms based on Darwinism, this work also studies Lamarckian evolutionary algorithms that, although not being biologically plausible, attained promising results in the tests.

[1]  Leandro Nunes de Castro,et al.  Fundamentals of natural computing: an overview , 2007 .

[2]  Phillip J. Windley.  Digital identity , 2005 .

[3]  JoyceRick,et al.  Identity authentication based on keystroke latencies , 1990 .

[4]  Sungzoon Cho,et al.  Web-Based Keystroke Dynamics Identity Verification Using Neural Network , 2000, J. Organ. Comput. Electron. Commer..

[5]  Kim W. C. Ku,et al.  Approaches to combining local and evolutionary search for training neural networks: a review and some new results , 2003 .

[6]  Dawn M. Cappelli,et al.  Insider Threat Study: Illicit Cyber Activity in the Information Technology and Telecommunications Sector , 2008 .

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

[8]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[9]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[10]  Martin P. Loeb,et al.  CSI/FBI Computer Crime and Security Survey , 2004 .

[11]  John F. Kolen,et al.  Backpropagation is Sensitive to Initial Conditions , 1990, Complex Syst..

[12]  Roberto Di Pietro,et al.  Intrusion Detection Systems , 2008 .

[13]  Issa Traoré,et al.  Digital Fingerprinting Based on Keystroke Dynamics , 2008, HAISA.

[14]  R. Power.  CSI/FBI computer crime and security survey , 2001 .

[15]  Pingzhi Fan,et al.  Novel Impostors Detection in Keystroke Dynamics by Support Vector Machine , 2004, PDCAT.

[16]  Liang Wang,et al.  Behavioral Biometrics For Human Identification: Intelligent Applications , 2009 .

[17]  Patrick Elftmann.  Secure Alternatives to Password-based Authentication Mechanisms submitted , 2006 .

[18]  Gopal K. Gupta,et al.  Identity authentication based on keystroke latencies , 1990, Commun. ACM.

[19]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[20]  Juan Julián Merelo Guervós,et al.  Lamarckian Evolution and the Baldwin Effect in Evolutionary Neural Networks , 2006, ArXiv.

[21]  Cédric Tabin,et al.  Liberty Alliance Project , 2007 .

[22]  José Neves,et al.  A Lamarckian Approach for Neural Network Training , 2002, Neural Processing Letters.