As biometric applications are gaining popularity, there is increased concern over the loss of privacy and potential misuse of biometric data held in central repositories. Biometric template protection mechanisms suggested in recent years aim to address these issues by securing the biometric data in a template or other structure such that it is suitable for authentication purposes, while being protected against unauthorized access or crosslinking attacks. We propose a biometric authentication framework for enhancing privacy and template security, by layering multiple biometric modalities to construct a multi-biometric template such that it is dicult to extract or separate the individual layers. Thus, the framework uses the subject's own biometric to conceal her biometric data, while it also enjoys the performance benets because of the use of multiple modalities. The resulting biometric template is also cancelable if the system is implemented with cancelable biometrics such as voice. We present two dierent realizations of this idea: one combining two dierent ngerprints and another one combining a ngerprint and a spoken passphrase. In either case, both biometric samples are required for successful authentication, leading to increased security, in addition to privacy gains. The performance of the proposed framework is evaluated using the FVC 2000-2002 and NIST ngerprint databases, and the TUBITAK MTRD speaker database. Results show only a small degradation in EER compared to a state-of-the-art ngerprint verication system and high identication rates, while cross-link rates are low even with very small databases. |