Abstract
Cancelable biometric recognition techniques play a vital role in the privacy and security of remote surveillance systems to keep the genuine users' confidential data safe and away from intruders. This research work presents an efficient cancelable biometric recognition framework that exploits an irreversible hybrid encryption algorithm. It incorporates Deoxyribonucleic, Ribonucleic Acid sequence (DNA and RNA) encryption technique, and an evolutionary optimization technique, namely Genetic Algorithms (GAs). These techniques are employed to create completely deformed templates from their original ones. Hence, the main contribution is introducing a novel biometric security framework that achieves unique randomness characteristics using RNA and DNA sequences and the evolutionary GA technique. The proposed framework produces entirely deformed biometric templates by ciphering the main discriminative features of the biometric traits of the authorized clients. It is firstly initialized by creating several encrypted biometric images for the original users with the logistic map. After that, the initially encrypted images are transformed into vectors of a binary array. Then, they are converted to their corresponding introns, and exons, and consequently, their relevant codons are stored in the cloud database. These relevant codons are replaced by new ones after generating encrypted RNA lists. The utilized encryption key for each template is extracted from the original biometric image through excessive permutations between pixels. The GA optimization technique is applied to select the most convenient biometric features. Finally, after employing the GA-based cross-over and mutation operations, the chosen features are used to generate the cancelable biometric traits. To assess the proposed framework, six different biometric databases are considered. These databases are Olivetti Research Laboratory (ORL) Faces (gray), CASIA v.5 Faces (color), UPOL Iris (gray), Indian Institute of Technology Delhi (IIT Delhi) Ear (color and gray), Fingerprint, and CASIA Palmprint (color and gray). The security performance of the proposed encryption algorithm is compared to those of recent studies in this field, such as Optical Scanning Holography (OSH) and Double Random Phase Encoding (DRPE). The simulation results prove the superior performance of the proposed framework in terms of all adopted evaluation metrics. The proposed framework provides high Area under the Receiver Operating Characteristic (AROC) curve that reaches 0.9990, low False Acceptance Rate (FAR) of 0.0015, more uniform histograms, high correlation values for genuine users, and completely hidden biometric features. In addition, from the security perspective, the proposed framework achieves good entropy, Unified Average Changing Intensity (UACI), and Number of Pixels Change Rate (NPCR) values that reach 7.9960, 33.55%, and 99.65%, respectively.