Cancelable Biometric Recognition With ECGs: Subspace-Based

Relying on physiological or behavioral traits for identity recognition, biometric technologies offer several advantages over conventional possession-and knowledge-based approaches and are now widely used in diverse applications. However, as most biometrics (e.g., fingerprints, irises, etc.) in use are extrinsic, susceptible to replay attacks, and could result in the disclosure of individuals' physiological and pathological conditions, security and privacy concerns must be considered. In this paper, several electrocardiogram (ECG)-based cancelable biometric schemes are proposed to mitigate such concerns. The intrinsic and dynamic nature of ECGs and their inherent indication of life make them extremely difficult to steal or counterfeit. Using the concept of signal subspace collapsing, distinct biometric templates associated with an individual's ECGs can be constructed such that it is possible to revoke a compromised template like a password. By incorporating different strategies for common subspace suppression, the well-known multiple signal classification method can effectively determine the identity of any individual just via his/her ECGs. Unlike existing cancelable biometrics, the recognition can be accomplished without knowledge of the distortion transformation, which further increases the difficulty of recovering the original ECGs from their templates. Various experiments with real ECGs from 285 subjects are conducted to illustrate the efficacy of the proposed schemes.