A Novel Biometric Authentication for ATM Security

A large portion of system breaches are caused by authentication failure. A central theme of authentication is to authenticate users using characteristics intrinsically linked with human users rather than some external factors. But current authentication methods, whether proxy based or biometrics based, are not user-centric and/or endanger users’ security and privacy. The proposed work is a biometrics based user-centric authentication approach. This method involves introducing a BioCapsule (BC), securely fusing the user’s biometrics with the user data, generating a BioCapsule and employing BCs for authentication. The user data used in this approach consist of user name, date of birth, address and account number which combines together forming a Reference Subject (RS). Such an approach is user friendly, identity bearing yet privacy-preserving, resilient, and revocable once a BC is compromised. The proposed model can be applied for biometric ATMs which replaces card system by biometric technology for operating ATMs. During authentication, the user is required to provide another sample of the users biometric characteristics. This is matched with the one in the database, and if the two samples are the same, then the user is considered to be a valid user. Proposed model provides high security in authentication which also protects service user from unauthorized access.