AN ENHANCED CYBER SECURITY FOR DORSAL FINGER KNUCKLE PATTERNS AND FINGER NAILS RECOGNITION SYSTEM BASED ON A CONCATENATED DEEP LEARNING MODEL WITH GRAIN-128A ENCRYPTION ALGORITHM

Abstract

The shift to biometric systems where unique qualities of a user used in place of standard passwords has brought a significant change in cybersecurity. The biometrics which consist of patterns of finger knuckles and fingernails give accurate and reliable identity recognition, and therefore minimize chances of unauthorized access and impersonation. The massive advancement of deep learning models allows the extraction of accurate biometric information in the images with the help of convolutional neural networks (CNNs), which are after that integrated to highly discriminative and consistent feature space. This high level of integration can help to build greater recognition strength and the safety of cryptographic keys that are produced by biometric features which is why this strategy can be chosen as one of the cornerstones in developing the safe biometric recognition systems that can help to build cybersecurity in the contemporary settings. This research introduces an enhanced cybersecurity for a dorsal finger knuckle pattern and finger nail recognition system, namely (ECS-DFKPFNRS), depending on an integrated feature deep learning (DL) with the cryptography algorithm.  This ECS-DFKPFNRS utilizes nineteen key components of the dorsal finger knuckle pattern of ten fingers for concatenated fusion recognition of all the features extracted. This system applies a concatenated DL model to four pre-trained models: InceptionNetV3, ResNet50, DenseNet201, and MobileNet-V3. To conduct this, the ECS-DFKPFNRS utilizes a new segmentation method that relies on the Hands Landmark Module (MediaPipe Module) to detect key knuckle hand components (Five-Basic, Five-Major, Four-Minor, and the fingernails) for both hands. After that, the concatenated fusion feature vectors extracted from the concatenated DL model will be utilized to generate a symmetric key (secret key) by the Rubik's cube technique. This technique will be improved by incorporating logistic scrambling, permutations, and SHA-512 hashing; subsequently, these keys to generated after the enhanced Rubik’s cube technique and will be utilized to encrypt biometric data by employing the lightweight Grain-128a algorithm. This is an integrated deep feature for FKP and FN and encryption, aiming to guarantee confidentiality and integrity against statistical attacks. 11,076K Hands and the ’Poly U HD’ datasets were utilized to analyze and evaluate this system. The system which was proposed was more effective on these datasets with outstanding security measures: NPCR (99.95% and 99.63%), UACI (30.23% and 30.21%), and resistance to statistical attacks. It is demonstrated in this study that the combination of DL and biometric encryption improves the reliability of biometric data and biometric robustness, which improves cybersecurity and digital biometric identity protection.