Abstract

This paper addresses the growing security concerns in cloud computing by proposing a robust and unobtrusive data protection mechanism. The study leverages secure, unobtrusive biometrics to enhance the security of data stored in the cloud. Cloud computing’s scalability and cost-effectiveness have driven its widespread adoption, yet securing sensitive data remains a challenge as cyberattacks on cloud infrastructures increase. To tackle this issue, a comprehensive framework is presented that integrates biometric authentication and encryption algorithms to protect data at rest in the cloud. The approach employs biometric traits, such as fingerprints, iris patterns, or facial features, to generate encryption keys, providing an additional security layer without burdening users. The methodology includes data preprocessing, feature extraction, biometric cancellation and authentication, and file upload and protection. Initially, facial features from unconstrained images are normalized and resized during preprocessing. A convolutional neural network (CNN) then extracts discriminative features. These features undergo biometric cancellation using the Lorenz chaotic algorithm and compressive sensing generalized likelihood ratio test (CS-GLRT) algorithm, ensuring enhanced security during recognition. The advanced encryption standard (AES) further secures the data. After successful authentication, files are uploaded and protected using an application programming interface (API) secured by AES. The proposed framework was evaluated using machine learning models, including support vector machines (SVM), random forest (RF), logistic regression (LR), and extreme gradient boosting (XGBoost). The dataset was split into 80% for training and 20% for testing, with each model trained for 100 epochs. The results indicate that the SVM classifier achieved the highest accuracy at 99.8%, making it the most suitable for unconstrained face image classification. This work demonstrates a novel and effective approach to safeguarding cloud-stored data, addressing critical security concerns while maintaining user convenience.

Keywords

Cloud computing security, Biometric authentication, Data encryption, Machine learning, Advanced encryption standard, Convolutional neural networks.

References

[1] Gupta S, Maple C, Crispo B, Raja K, Yautsiukhin A, Martinelli F. A survey of human-computer interaction (HCI) & natural habits-based behavioural biometric modalities for user recognition schemes. Pattern Recognition. 2023; 139:109453.

[2] Li Y. Research and application of deep learning in image recognition. In 2nd international conference on power, electronics and computer applications 2022 (pp. 994-9). IEEE.

[3] Wang S, Deng G, Hu J. A partial hadamard transform approach to the design of cancelable fingerprint templates containing binary biometric representations. Pattern Recognition. 2017; 61:447-58.

[4] Yang W, Wang S, Hu J, Zheng G, Valli C. A fingerprint and finger-vein based cancelable multi-biometric system. Pattern Recognition. 2018; 78:242-51.

[5] Shahzad M, Wang S, Deng G, Yang W. Alignment-free cancelable fingerprint templates with dual protection. Pattern Recognition. 2021; 111:107735.

[6] Bedari A, Wang S, Yang W. Design of cancelable MCC-based fingerprint templates using dyno-key model. Pattern Recognition. 2021; 119:108074.

[7] Maiorana E. A survey on biometric recognition using wearable devices. Pattern Recognition Letters. 2022; 156:29-37.

[8] Hammadi OI, Abas AD, Ayed KH. Face recognition using deep learning methods a review. International Journal of Engineering & Technology. 2018; 7:6181-8.

[9] Melzi P, Tolosana R, Vera-rodriguez R, Kim M, Rathgeb C, Liu X, et al. FRCSyn-ongoing: nenchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems. Information Fusion. 2024; 107:1-19.

[10] Zulfiqar M, Syed F, Khan MJ, Khurshid K. Deep face recognition for biometric authentication. In international conference on electrical, communication, and computer engineering 2019 (pp. 1-6). IEEE.

[11] Semwal A, Londhe ND. A multi-stream spatio-temporal network based behavioural multiparametric pain assessment system. Biomedical Signal Processing and Control. 2024; 90:105820.

[12] Singhal N, Ganganwar V, Yadav M, Chauhan A, Jakhar M, Sharma K. Comparative study of machine learning and deep learning algorithm for face recognition. Jordanian Journal of Computers and Information Technology. 2021; 7(3):313-25.

[13] Sawat DD, Hegadi RS. Unconstrained face detection: a deep learning and machine learning combined approach. CSI Transactions on ICT. 2017; 5:195-9.

[14] Moghekar R, Ahuja S. Face recognition in unconstrained environment using deep learning. In soft computing for intelligent systems: proceedings of ICSCIS 2020 (pp. 241-53). Springer Singapore.

[15] Adetunji TO. Machine learning algorithms in facial identity verification for computer-based assessments. Acta Electronica Malaysia. 2024; 8(2):54-9.

[16] Qasim KR, Qasim SS. Force field feature extraction using FAST algorithm for face recognition performance. In journal of physics: conference series 2021 (p. 012195). IOP Publishing.

[17] Vakhshiteh F, Nickabadi A, Ramachandra R. Adversarial attacks against face recognition: a comprehensive study. IEEE Access. 2021; 9:92735-56.

[18] Sharma R. Biometric authentication using lightweight convolutional neural network. In international students' conference on electrical, electronics and computer science 2024 (pp. 1-6). IEEE.

[19] Kauba C, Piciucco E, Maiorana E, Gomez-barrero M, Prommegger B, Campisi P, et al. Towards practical cancelable biometrics for finger vein recognition. Information Sciences. 2022; 585:395-417.

[20] Liu Y, Zhang X, Li Y, Zhou J, Li X, Zhao G. Graph-based facial affect analysis: a review. IEEE Transactions on Affective Computing. 2022; 14(4):2657-77.

[21] Ma Q, Li B, Liu G, Li Y, Wang Y, Gu M, et al. Cancelable face template protection based on deep neural network. In 7th international conference on signal and image processing 2022 (pp. 659-64). IEEE.

[22] Helmy M, El-shafai W, El-rabaie ES, El-dokany IM, Abd EFE. A hybrid encryption framework based on Rubik’s cube for cancelable biometric cyber security applications. Optik. 2022; 258:168773.

[23] Acar A. Privacy-aware security applications in the era of internet of things. Electronic Theses and Dissertations, Florida International University. 2020.

[24] Sudhakar T, Gavrilova M. Deep learning for multi-instance biometric privacy. ACM Transactions on Management Information Systems. 2020; 12(1):1-23.

[25] Abdellatef E, Ismail NA, Abd Elrahman SE, Ismail KN, Rihan M, Abd El-Samie FE. Cancelable fusion-based face recognition. Multimedia Tools and Applications. 2019; 78:31557-80.

[26] Almomani I, El-Shafai W, AlKhayer A, Alsumayt A, Aljameel S, Alissa K. Proposed biometric security system based on deep learning and chaos algorithms. Computers, Materials & Continua. 2023; 74(2):3515-37.

[27] Hassaballah M, Aly S. Face recognition: challenges, achievements and future directions. IET Computer Vision. 2015; 9(4):614-26.

[28] Abdellatef E, Ismail NA, Abd Elrahman SE, Ismail KN, Rihan M, Abd El-Samie FE. Cancelable multi-biometric recognition system based on deep learning. The Visual Computer. 2020; 36:1097-109.

Cite this article