Guest Editorial Special Issue on Biometric Spoofing and Countermeasures

While biometrics technology has created new solutions to person authentication and has evolved to play a critical role in personal, national and global security, the potential for the technology to be fooled or spoofed is now widely acknowledged. For example, fingerprint verification systems can be spoofed with a synthetic material, such as gelatine, inscribed with the fingerprint ridges of an enrolled individual. Iris and face recognition systems are vulnerable to printed photographs or video sequences of an enrolled user’s eye or face. Speaker recognition systems can be spoofed through the use of replayed, synthesized or converted speech. The interest in spoofing and countermeasures has grown significantly in recent years: several well known cases publicized in the mass media have shown that the biometric authentication modules in some of today’s most popular consumer electronics devices are vulnerable to spoofing; there are now numerous special sessions, tutorials, competitive evaluations and international standards (ISO/IEC JTC SC37) on the topic; commercial biometric authentication solutions are increasingly equipped with liveness detection; Europe funded a largescale collaborative project, known as TABULA RASA1, to investigate the threat of spoofing and to develop dedicated countermeasures. While efforts to develop countermeasures are now well under way and some promising solutions have emerged, there are some common shortcomings in current research methodologies. Existing countermeasures, designed to detect and deflect spoofing attacks, are typically learned using training data produced using exactly the same spoofing method that is to be detected. This practice amounts to the biased use of prior knowledge which is clearly unrepresentative of a practical scenario in which the nature of the attack can never be known. At best, research results generated with such methodologies exaggerate countermeasure performance; at worst, they mask the true scale of the problem. This special issue was conceived to further the state-ofthe-art in biometrics spoofing countermeasures, to stimulate increased cross-fertilisation between the biometrics and information forensic communities and to encourage the development of reliable methodologies in spoofing and countermeasure assessment and solutions. In particular the aim was to foster a shift from current research methodologies and attack-specific countermeasures to novel methodologies and generalised countermeasures having the potential to protect biometric systems against varying or previously unseen attacks.