Online Signature Verification Algorithm Using Hill-Climbing Method

Abstract

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.