Privacy-Preserving Multi-Biometric Indexing Based on Frequent Binary Patterns

Abstract

The development of large-scale identification systems that ensure the privacy protection of enrolled subjects represents a major challenge. Biometric deployments that provide interoperability and usability by including efficient multibiometric solutions are a recent requirement. In the context of privacy protection, several template protection schemes have been proposed in the past. However, these schemes seem inadequate for indexing (workload reduction) in biometric identification systems. More specifically, they have been used in identification systems that perform exhaustive searches, leading to a degradation of computational efficiency. To overcome these limitations, we present an efficient privacy-preserving multi-biometric identification system that retrieves protected deep cancelable templates and is agnostic with respect to biometric characteristics and biometric template protection schemes. To this end, a multi-biometric binning scheme is designed to exploit the low intra-class variation properties contained in the frequent binary patterns extracted from different types of biometric characteristics. Experimental results reported on publicly available databases using state-ofthe-art Deep Neural Network (DNN)-based embedding extractors show that the protected multi-biometric identification system can reduce the computational workload to approximately 57% (indexing up to three types of biometric characteristics) and 53% (indexing up to two types of biometric characteristics), while simultaneously improving the biometric performance of the baseline biometric system at the high-security thresholds 1 .

Generation of Face Privacy-Protected Images Based on the Diffusion Model

“…The realism scale factor adjusts the similarity between the resulting image and the original image, ensuring that the generated image maintains authenticity while closely matching the appearance and style of real image data distribution. This is achieved by controlling specific image parameters, as indicated in Equation (13). g rea and M determine the value H to control the scale of the low-pass filter LP's downsampling and upsampling operations, which are part of the iterative latent variable refinement process to adjust the image's detail and realism during generation.…”

“…However, these methods directly remove facial information, resulting in compromised visual quality and reduced reusability. Subsequently, researchers shifted towards approaches centered on facial replacement [ 10 , 11 , 12 , 13 , 14 , 15 , 16 ]. This strategy aims to obfuscate the identity of the original face by substituting parts of it while retaining some facial features to maintain usability.…”