95 articles 

inria-00104811, version 1

Evaluating the Security of Handwriting Biometrics

Lucas Ballard () 1, Daniel Lopresti () 2, Fabian Monrose () 1

Tenth International Workshop on Frontiers in Handwriting Recognition (2006)

Abstract: Ongoing interest in biometric security has resulted in much work on systems that exploit the individuality of human behavior. In this paper, we study the use of handwritten passphrases in the context of authentication or cryptographic key generation. We demonstrate that accurate generative models for a targeted user's handwriting can be developed based only on captured static (offline) samples combined with pen-stroke dynamics learned from general population statistics. Our work suggests that such automated attacks are nearly as effective as skilled human forgers and hence deserve serious consideration when evaluating the security of systems that use handwriting as a biometric.

  • 1:  Computer Science Department
  • Johns HopkinsUniversity
  • 2:  Computer Science & Engineering Department (CSE)
  • Lehigh University, Bethlehem, USA
  • Domain : Computer Science/Document and Text Processing
    Computer Science/Computer Vision and Pattern Recognition
  • Keywords : Biometric security – online handwriting – performance evaluation – forgery threat models.
  • Comment : http://www.suvisoft.com
 
  • inria-00104811, version 1
  • oai:hal.inria.fr:inria-00104811
  • From: 
  • Submitted on: Monday, 9 October 2006 14:40:04
  • Updated on: Monday, 9 October 2006 14:44:35