ENHANCEMENT OF FINGERPRINT TEMPLATE PROTECTION AND PRIVACY PRESERVATION USING FULLY HOMOMORPHIC ENCRYPTION

Abstract

The transition from conventional or token-based passwords to biometric technologies because of the advantageous characteristics of biometrics traits is increasing daily. Nowadays, biometric technologies are utilised in applications such as border control, e-banking, e-health, etc. Biometric traits comprise biological traits (iris, face, fingerprint, etc) and behavioural traits (keystroke, signature, voice, etc). In contrast to other biometric traits, the fingerprint is the most utilised in most applications. Despite the advantages, biometric technologies have their drawbacks. The biometric data of an individual is unique since no two people have the same biometrics, and compromising this biometric data could have devastating results. This issue was addressed using the implementation of the Paillier cryptosystem, a partial homomorphic encryption scheme which only involves addition operations. This implementation suffers drawbacks when faced with complex computations such as the multiplication of two ciphertexts and faces ciphertext noise growth due to these complex computations. Thus, a need for fully homomorphic encryption which handles complex computation and manages noise growth through several techniques. This research work is aimed at enhancing fingerprint template protection and privacy preservation using fully homomorphic encryption. The proposed system was developed utilising the Brakerski/Fan-Vercauteren fully homomorphic encryption scheme implemented using the OpenFHE-Python library. The system was evaluated using the Neurotechnology CrossMatch dataset according to performance metrics including Accuracy, Genuine Acceptance Rate (GAR) and Equal Error Rate (EER). Results indicated that the Neurotechnology CrossMatch dataset achieved an accuracy of 84%, GAR of 84%, and EER of 16%. Therefore, the implementation of fully homomorphic encryption in biometrics achieves adequate accuracy despite both the encryption and decryption processes, thereby safeguarding the template, and preserving the user’s privacy.