Online Signature Verification Algorithm Using Hill-Climbing Method

Attacks using hill-climbing methods have been reported as a vulnerability of biometric authentication systems. In this paper, the author proposes a robust online signature verification algorithm against attacks using the hill-climbing method. Specifically, the attack considered in this paper is a hill-climbing forged data attack. Artificial forgeries are generated by using the hill-climbing method and the forgeries are input to a target system to be attacked. In order to generate a robust algorithm, the author proposes incorporating the hill-climbing method into an online signature verification algorithm. Preliminary experiments were performed using several online signature databases. The results show that the proposed algorithm improved the performance against this kind of attack. Equal Error Rate (EER) was improved from 88.3% to 1.2% when using a private database for evaluation.

[1]  Andy Adler,et al.  Biometric System Security , 2008 .

[2]  Toby Berger,et al.  Reliable On-Line Human Signature Verification Systems , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Naohisa Komatsu,et al.  A study on vulnerability in on-line writer verification system , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[4]  Réjean Plamondon,et al.  Automatic signature verification and writer identification - the state of the art , 1989, Pattern Recognit..

[5]  Ronny Martens,et al.  On-line signature verification: discrimination emphasised , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[6]  Pietro Perona,et al.  Visual Identification by Signature Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  L. Yang,et al.  Application of hidden Markov models for signature verification , 1995, Pattern Recognit..

[8]  Takashi Matsumoto,et al.  A Markov chain Monte Carlo algorithm for bayesian dynamic signature verification , 2006, IEEE Transactions on Information Forensics and Security.

[9]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[10]  Anil K. Jain,et al.  On-line signature verification, , 2002, Pattern Recognit..

[11]  A. Adler,et al.  Images can be regenerated from quantized biometric match score data , 2004, Canadian Conference on Electrical and Computer Engineering 2004 (IEEE Cat. No.04CH37513).

[12]  Hong Chang,et al.  SVC2004: First International Signature Verification Competition , 2004, ICBA.

[13]  Vishvjit S. Nalwa,et al.  Automatic On-line Signature Verification , 1997 .

[14]  Andy Adler.  Sample images can be independently restored from face recognition templates , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[15]  Julian Fiérrez,et al.  Bayesian Hill-Climbing Attack and Its Application to Signature Verification , 2007, ICB.