An Experimental Study on Random Projection Based Biometric Security

Rishabh Shukla, Harkeerat Kaur

Abstract: The safeguarding of biometric data is a crucial aspect of biometric authentication systems, and biometric template protection serves as a means to ensure the confidentiality of such information. In recent times, the utilization of random projection has surfaced as a viable technique for safeguarding biometric templates. This article delves deeper into the security of random projection-based techniques utilized for safeguarding biometric templates. The demonstration showcases that the security of biometric systems is compromised by non-invertibility attacks, as the protected template can be utilized by an attacker to accurately replicate the initial biometric template. A viable approach for executing non-invertibility attacks on systems, based on random projection is additionally furnished by us. The study conducted an experiment on two publicly accessible biometric datasets to demonstrate the vulnerability of random projection-based biometric template security methods. The proposed assault was utilized to recreate the original templates, highlighting the ease with which this could be accomplished. The results of our study emphasize the necessity for innovative methods in safeguarding biometric templates that are impervious to inversion.