Bridging the Gap: Creating Authentic Biometric Templates for Secure Authentication Systems

Fingerprints serve as a primary means of individually identifying individuals. However, employing fingerprints in online mode poses a significant privacy risk, since it is susceptible to several forms of attack. It is plagued by issues related to privacy and security. In response to this, we proposed an innovative approach to convert the original fingerprint into a secure template that may be retained and utilized for authentication purposes. The new templates bear a resemblance to the original human fingerprints and ensure privacy by possessing the characteristic of non-invertibility. This study presented a method for generating highly authentic fingerprint templates that ensure the capacity to revoke and cancel the stolen fingerprint. Throughout the training and testing phase, we utilized the dataset derived from the Vikriti-ID fingerprint. The collection has 25000 distinct fingerprint samples, divided into five classes, with each class containing 5,000 samples. Throughout the testing phase, the comprehensive performance was evaluated based on the matching performance including EER and AUC.