Fingerprint Template Protection: From Theory to Practice

One of the potential vulnerabilities in a biometric system is the leakage of biometric template information, which may lead to serious security and privacy threats. Most of the available template protection techniques fail to meet all the desired requirements of a practical biometric system like revocability, security, privacy, and high matching accuracy. In particular, protecting the fingerprint templates has been a difficult problem due to large intra-user variations (e.g., rotation, translation, nonlinear deformation, and partial prints). There are two fundamental challenges in any fingerprint template protection scheme. First, we need to select an appropriate representation scheme that captures most of the discriminatory information, but is sufficiently invariant to changes in finger placement and can be secured using available template protection algorithms. Secondly, we need to automatically align or register the fingerprints obtained during enrollment and matching without using any information that could reveal the features, which uniquely characterize a fingerprint. This chapter analyzes how these two challenges are being addressed in practice and how the design choices affect the trade-off between the security and matching accuracy. Though much progress has been made over the last decade, we believe that fingerprint template protection algorithms are still not sufficiently robust to be incorporated into practical fingerprint recognition systems. Anil K. Jain Department of Computer Science & Engineering, Michigan State University, East Lansing, MI 48824, USA and Department of Brain & Cognitive Engineering, Korea University, Seoul. e-mail: [email protected], Karthik Nandakumar Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore. e-mail: [email protected], Abhishek Nagar Department of Computer Science & Engineering, Michigan State University, East Lansing, MI 48824, USA. e-mail: [email protected]