Open Access

ARTICLE

Proposed Biometric Security System Based on Deep Learning and Chaos Algorithms

Iman Almomani^1,2, Walid El-Shafai^1,3,*, Aala AlKhayer¹, Albandari Alsumayt⁴, Sumayh S. Aljameel⁵, Khalid Alissa⁶

1 Security Engineering Lab, Computer Science Department, Prince Sultan University, Riyadh, 11586, Saudi Arabia
2 Computer Science Department, King Abdullah II School of Information Technology, The University of Jordan, 11942, Jordan
3 Department of Electronics and Electrical Communications Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf, 32952, Egypt
4 Computer Science Department, Applied College, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia
5 Computer Science Department, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia
6 SAUDI ARAMCO Cybersecurity Chair, Networks and Communications Department, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia

* Corresponding Author: Walid El-Shafai. Email:

Computers, Materials & Continua 2023, 74(2), 3515-3537. https://doi.org/10.32604/cmc.2023.033765

Received 27 June 2022; Accepted 16 August 2022; Issue published 31 October 2022

Abstract

Nowadays, there is tremendous growth in biometric authentication and cybersecurity applications. Thus, the efficient way of storing and securing personal biometric patterns is mandatory in most governmental and private sectors. Therefore, designing and implementing robust security algorithms for users’ biometrics is still a hot research area to be investigated. This work presents a powerful biometric security system (BSS) to protect different biometric modalities such as faces, iris, and fingerprints. The proposed BSS model is based on hybridizing auto-encoder (AE) network and a chaos-based ciphering algorithm to cipher the details of the stored biometric patterns and ensures their secrecy. The employed AE network is unsupervised deep learning (DL) structure used in the proposed BSS model to extract main biometric features. These obtained features are utilized to generate two random chaos matrices. The first random chaos matrix is used to permute the pixels of biometric images. In contrast, the second random matrix is used to further cipher and confuse the resulting permuted biometric pixels using a two-dimensional (2D) chaotic logistic map (CLM) algorithm. To assess the efficiency of the proposed BSS, (1) different standardized color and grayscale images of the examined fingerprint, faces, and iris biometrics were used (2) comprehensive security and recognition evaluation metrics were measured. The assessment results have proven the authentication and robustness superiority of the proposed BSS model compared to other existing BSS models. For example, the proposed BSS succeeds in getting a high area under the receiver operating characteristic (AROC) value that reached 99.97% and low rates of 0.00137, 0.00148, and 0.00157 for equal error rate (EER), false reject rate (FRR), and a false accept rate (FAR), respectively.

---

Keywords

---