Enhancing Multifactor Authentication Using Machine Learning Techniques
Article Sidebar
Main Article Content
Abstract
Securing access to distributed database systems presents unique challenges because of their decentralized nature and exposure to multipoint threats. Traditional single-factor authentication mechanisms, such as passwords or PINs, are insufficient in such environments, prompting the need for more resilient solutions. This study proposes a biometric-based multifactor authentication (MFA) framework that combines fingerprint and facial modalities through a unified machine learning (ML) pipeline. ML plays a crucial role in enhancing classification performance by enabling the system to learn complex patterns across biometric inputs. The framework standardizes input preprocessing (by applying grayscale conversion, histogram equalization, and normalization) and employs the histogram of oriented gradients (HOG) technique for feature extraction. To improve classification performance and generalizability, three decision-level ensemble models are used: support vector machine (SVM) integrated with random forest (RF), stochastic gradient descent (SGD), and eXtreme gradient boosting (XGBoost). These hybrid combinations exploit the complementary strengths of different classifiers, such as margin optimization, ensemble learning, and fast convergence, resulting in superior accuracy compared with standalone models. All the models were trained and evaluated via a 10-fold cross-validation scheme on the family fingerprint dataset and face recognition dataset under consistent conditions. The experimental results indicate that the SVM with the RF model achieves the highest accuracy, with scores of 0.92 for fingerprint recognition and 0.97 for facial recognition. These outcomes underscore the framework’s suitability for high-security applications, particularly in distributed database environments where reliable and adaptive authentication is essential.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
[1] S. Zou, “A robust and effective 3-factor authentication protocol for smart factory in IIoT,” Comput. Commun, vol. 220, pp. 81–93,, doi: 10.1016/j.comcom.2024.04.011.
[2] G. . Ali , Trans., “Integration of Artificial Intelligence, Blockchain, and Quantum Cryptography for Securing the Industrial Internet of Things (IIoT): Recent Advancements and Future Trends”, Applied Data Science and Analysis, vol. 2025, pp. 19–82, Mar. 2025, doi: 10.58496/ADSA/2025/004.
[3] D. Wang, J. Zhou, M. Masdari, S. N. Qasem, and B. T. Sayed, “Security in wireless body area networks via anonymous authentication: Comprehensive literature review, scheme classification, and future challenges,” Ad Hoc Networks, vol. 153, p. 103332, doi: 10.1016/j.adhoc.2023.103332.
[4] J. Al-Saraireh and M. R. AlJa’afreh, “Keystroke and swipe biometrics fusion to enhance smartphones authentication,” Comput. Secur, vol. 125, p. 103022, doi: 10.1016/j.cose.2022.103022.
[5] M. Saqib, B. Jasra, and A. H. Moon, “A lightweight three factor authentication framework for IoT based critical applications,” J. King Saud Univ. - Comput. Inf. Sci, vol. 34, no. 9, pp. 6925–6937,, doi: 10.1016/j.jksuci.2021.07.023.
[6] S. Tanwar, D. Ribadiya, P. Bhattacharya, A. R. Nair, N. Kumar, and M. Jo, “Fusion of blockchain and IoT in scientific publishing: Taxonomy, tools, and future directions,” Futur. Gener. Comput. Syst, vol. 142, pp. 248–275,, doi: 10.1016/j.future.2022.12.036.
[7] G. Ali, “Enhancing Cybersecurity in Smart Education with Deep Learning and Computer Vision: A Survey”,” Mesopotamian J. Comput. Sci., vol. 2025, pp. 115–158,, doi: 10.58496/MJCSC/2025/008.
[8] Z. Ali, S. A. Chaudhry, K. Mahmood, S. Garg, Z. Lv, and Y. B. Zikria, “A clogging resistant secure authentication scheme for fog computing services,” Comput. Networks, vol. 185, p. 107731, doi: 10.1016/j.comnet.2020.107731.
[9] “Big Data Predictive Analytics for Personalized Medicine: Perspectives and Challenges,” Applied Data Science and Analysis, vol. 2024 SE-Articles. pp. 32–38. doi: 10.58496/ADSA/2024/004.
[10] H. A. Alameen and F. Rabee, “Blockchain-Based Metadata Management in Distributed File Systems”,” Mesopotamian J. CyberSecurity, vol. 5, no. 2, pp. 349–360,, doi: 10.58496/MJCS/2025/022.
[11] S. M. Darwish and A. A. Ismail, “An Evolutionary Biometric Authentication Model for Finger Vein Patterns BT,” in Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2020,”, pp. 271–281.
[12] S. A. Hussein, “Integrating Law, Cybersecurity, and AI: Deep Learning for Securing Iris-Based Biometric Systems”,” Mesopotamian J. CyberSecurity, vol. 5, no. 2, pp. 319–336,, doi: 10.58496/MJCS/2025/020.
[13] J. J. Hathaliya, S. Tanwar, and R. Evans, “Securing electronic healthcare records: A mobile-based biometric authentication approach,” J. Inf. Secur. Appl, vol. 53, p. 102528, doi: 10.1016/j.jisa.2020.102528.
[14] R. Srivastva, Y. N. Singh, and A. Singh, “Statistical independence of ECG for biometric authentication,” Pattern Recognit, vol. 127, p. 108640, doi: 10.1016/j.patcog.2022.108640.
[15] R. A. Aljanabi, Z. Al-Qaysi, and M. S. Suzani, “Deep Transfer Learning Model for EEG Biometric Decoding”,” Appl. Data Sci. Anal., vol. 2024, pp. 4–16,, doi: 10.58496/ADSA/024/002.
[16] G. Choi, G. Ziyang, J. Wu, C. Esposito, and C. Choi, “Multi-modal Biometrics Based Implicit Driver Identification System Using Multi-TF Images of ECG and EMG,” Comput. Biol. Med, vol. 159, p. 106851, doi: 10.1016/j.compbiomed.2023.106851.
[17] M. Singh, N. Baranwal, K. N. Singh, A. K. Singh, and H. Zhou, “Deep learning-based biometric image feature extraction for securing medical images through data hiding and joint encryption–compression,” J. Inf. Secur. Appl, vol. 79, p. 103628, doi: 10.1016/j.jisa.2023.103628.
[18] E. A. Alkeem, “Robust Deep Identification using ECG and Multimodal Biometrics for Industrial Internet of Things,” Ad Hoc Networks, vol. 121, p. 102581, doi: 10.1016/j.adhoc.2021.102581.
[19] A. S. Sonal and C. Kant, “Optimized hybrid SVM-RF multibiometric framework for enhanced authentication using fingerprint, iris, and face recognition,” PeerJ Comput. Sci, vol. 11, doi: 10.7717/PEERJ-CS.2699.
[20] J. Han, “CNN-Based Multi-Factor Authentication System for Mobile Devices Using Faces and Passwords,” Appl. Sci, vol. 14, no. 12, doi: 10.3390/app14125019.
[21] Z. Wen, S. Han, Y. Yu, X. Xiang, S. Lin, and X. Xu, “Empowering robust biometric authentication: The fusion of deep learning and security image analysis,” Appl. Soft Comput, vol. 154, p. 111286, doi: 10.1016/j.asoc.2024.111286.
[22] C. Vensila and A. B. Wesley, “Multimodal biometrics authentication using extreme learning machine with feature reduction by adaptive particle swarm optimization,” Vis. Comput, vol. 40, no. 3, pp. 1383–1394,, doi: 10.1007/s00371-023-02856-4.
[23] S. Bharadwaj, P. Amin, D. J. Ramya, and S. Parikh, “Reliable human authentication using AI-based multibiometric image sensor fusion: Assessment of performance in information security,” Meas. Sensors, vol. 33, no. March, p. 101140, doi: 10.1016/j.measen.2024.101140.
[24] D. Maiti and D. Das, “FAMILY FINGERPRINT DATASET,” 2023.
[25] V. Patel, “Face Recognition Dataset.”
[26] T. J. Mohammed et al., “Convalescent-plasma-transfusion intelligent framework for rescuing COVID-19 patients across centralised/decentralised telemedicine hospitals based on AHP-group TOPSIS and matching component,” Appl. Intell., no. Icci, 2021, doi: 10.1007/s10489-020-02169-2.
[27] A. R. J. Mitchell, D. Ahlert, C. Brown, M. Birge, and A. Gibbs, “Electrocardiogram-based biometrics for user identification – Using your heartbeat as a digital key.,” J. Electrocardiol., vol. 80, pp. 1–6, 2023, doi: https://doi.org/10.1016/j.jelectrocard.2023.04.001.
[28] A Comparative study of Chest Radiographs and Detection of The Covid 19 Virus Using Machine Learning Algorithm,” Mesopotamian J. Comput. Sci., vol. 2024, pp. 34–43, 2024, doi: 10.58496/MJCSC/2024/004.
[29] “Advanced Image Processing Techniques for Automated Detection of Healthy and Infected Leaves in Agricultural Systems,” Mesopotamian J. Comput. Sci., vol. 2024, pp. 44–52, 2024, doi: 10.58496/MJCSC/2024/006.
[30] L. Wan, K. Liu, H. A. Mengash, N. Alruwais, M. Al Duhayyim, and K. Venkatachalam, “Deep learning-based photoplethysmography biometric authentication for continuous user verification,” Appl. Soft Comput., vol. 156, p. 111461, 2024, doi: https://doi.org/10.1016/j.asoc.2024.111461.
[31] S. S. Thenuwara, C. Premachandra, and H. Kawanaka, “A multi-agent based enhancement for multimodal biometric system at border control,” Array, vol. 14, p. 100171, 2022, doi: https://doi.org/10.1016/j.array.2022.100171.
[32] I. Boucherit, M. O. Zmirli, H. Hentabli, and B. A. Rosdi, “Finger vein identification using deeply-fused Convolutional Neural Network,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 3, pp. 646–656, 2022, doi: https://doi.org/10.1016/j.jksuci.2020.04.002.
[33] Y.-J. Kang, J.-I. Yoo, Y.-H. Cha, C. H. Park, and J.-T. Kim, “Machine learning–based identification of hip arthroplasty designs,” J. Orthop. Transl., vol. 21, pp. 13–17, 2020, doi: https://doi.org/10.1016/j.jot.2019.11.004.
[34] R. G. Babu, P. Karthika, and G. Manikandan, “Polynomial Equation Based Localization and Recognition Intelligent Vehicles Axis using Wireless Sensor in MANET,” Procedia Comput. Sci., vol. 167, pp. 1281–1290, 2020, doi: https://doi.org/10.1016/j.procs.2020.03.444.
[35] N. Aghnia Farda, J.-Y. Lai, J.-C. Wang, P.-Y. Lee, J.-W. Liu, and I.-H. Hsieh, “Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques.,” Injury, vol. 52, no. 3, pp. 616–624, Mar. 2021, doi: 10.1016/j.injury.2020.09.010.
[36] A. A. Al-Hillali and S. S. Omran, “Half Iris Matching Based on RED Algorithm,” Int. J. Informatics Commun. Technol., vol. 5, no. 1, p. 21, 2016, doi: 10.11591/ijict.v5i1.pp21-27.
[37] N. Dominic, Daniel, T. W. Cenggoro, A. Budiarto, and B. Pardamean, “Transfer learning using inception-resnet-v2 model to the augmented neuroimages data for autism spectrum disorder classification,” Commun. Math. Biol. Neurosci., vol. 2021, pp. 1–21, 2021, doi: 10.28919/cmbn/5565.
[38] Y. Wang, H. Lu, X. Qin, and J. Guo, “Residual Gabor convolutional network and FV-Mix exponential level data augmentation strategy for finger vein recognition,” Expert Syst. Appl., vol. 223, p. 119874, 2023, doi: https://doi.org/10.1016/j.eswa.2023.119874.
[39] Z. Ding et al., “Multi-resolution 3D-HOG feature learning method for Alzheimer’s Disease diagnosis,” Comput. Methods Programs Biomed., vol. 214, p. 106574, 2022, doi: https://doi.org/10.1016/j.cmpb.2021.106574.
[40] K. Fatema et al., “Heliyon Development of an automated optimal distance feature-based decision system for diagnosing knee osteoarthritis using segmented X-ray images,” Heliyon, vol. 9, no. 11, p. e21703, 2023, doi: 10.1016/j.heliyon.2023.e21703.
[41] A. K. Sharma et al., “HOG transformation based feature extraction framework in modified Resnet50 model for brain tumor detection,” Biomed. Signal Process. Control, vol. 84, p. 104737, 2023, doi: https://doi.org/10.1016/j.bspc.2023.104737.
[42] A. Sharma, D. P. Yadav, H. Garg, M. Kumar, B. Sharma, and D. Koundal, “Bone Cancer Detection Using Feature Extraction Based Machine Learning Model,” Comput. Math. Methods Med., vol. 2021, 2021, doi: 10.1155/2021/7433186.
[43] M. Mebarkia, A. Meraoumia, L. Houam, and S. Khemaissia, “X-ray image analysis for osteoporosis diagnosis: From shallow to deep analysis,” Displays, vol. 76, p. 102343, 2023, doi: https://doi.org/10.1016/j.displa.2022.102343.
[44] S. Ramachandra and S. Ramachandran, “Region specific and subimage based neighbour gradient feature extraction for robust periocular recognition,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 10, Part A, pp. 7961–7973, 2022, doi: https://doi.org/10.1016/j.jksuci.2022.07.013.
[45] S. Demir, S. Key, T. Tuncer, and S. Dogan, “An exemplar pyramid feature extraction based humerus fracture classification method,” Med. Hypotheses, vol. 140, p. 109663, 2020, doi: https://doi.org/10.1016/j.mehy.2020.109663.
[46] H. Abubakar, F. Al-Turjman, Z. S. Ameen, A. S. Mubarak, and C. Altrjman, “A hybridized feature extraction for COVID-19 multi-class classification on computed tomography images,” Heliyon, vol. 10, no. 5, p. e26939, 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e26939.
[47] T. J. Mohammed, A Systematic Review of Artificial Intelligence in Orthopaedic Disease Detection: A Taxonomy for Analysis and Trustworthiness Evaluation, vol. 17, no. 1. Springer Netherlands.
[48] F. Han, X. Li, J. Zhao, and F. Shen, “A unified perspective of classification-based loss and distance-based loss for cross-view gait recognition,” Pattern Recognit, vol. 125, p. 108519, doi: 10.1016/j.patcog.2021.108519.
[49] M. K. Benkaddour and A. Bounoua, “Feature extraction and classification using deep convolutional neural networks, PCA and SVC for face recognition,” Trait. du Signal, vol. 34, no. 1–2, pp. 77–91,, doi: 10.3166/TS.34.77-91.
[50] S. D. Mehta and R. Sebro, “Random forest classifiers aid in the detection of incidental osteoblastic osseous metastases in DEXA studies,” Int. J. Comput. Assist. Radiol. Surg, vol. 14, no. 5, pp. 903–909,, doi: 10.1007/s11548-019-01933-1.
[51] S. K. Singh and A. Chaturvedi, “Leveraging deep feature learning for wearable sensors based handwritten character recognition,” Biomed. Signal Process. Control, vol. 80, p. 104198, doi: 10.1016/j.bspc.2022.104198.
[52] R. C. H. Chang, C. Y. Wang, Y. H. Li, and C. Chiu, “Design of Low-Complexity Convolutional Neural Network Accelerator for Finger Vein Identification System,” Sensors, vol. 23, no. 4, doi: 10.3390/s23042184.
[53] A. Ahmed, A. S. Imran, A. Manaf, Z. Kastrati, and S. M. Daudpota, “Enhancing wrist abnormality detection with YOLO: Analysis of state-of-the-art single-stage detection models,” Biomed. Signal Process. Control, vol. 93, no. January, p. 106144, doi: 10.1016/j.bspc.2024.106144.
[54] V. A. Ardeti, “Development of real time ECG monitoring and unsupervised learning classification framework for cardiovascular diagnosis,” Biomed. Signal Process. Control, vol. 88, p. 105553, doi: 10.1016/j.bspc.2023.105553.
[55] A. S. Albahri et al., “A trustworthy and explainable framework for benchmarking hybrid deep learning models based on chest X-ray analysis in CAD systems,” Int. J. Inf. Technol. Decis. Mak., pp. 1–54, 2024.
[56] S. Guinebert, E. Petit, V. Bousson, S. Bodard, N. Amoretti, and B. Kastler, “Automatic semantic segmentation and detection of vertebras and intervertebral discs by neural networks,” Comput. Methods Programs Biomed. Updat., vol. 2, p. 100055, 2022, doi: https://doi.org/10.1016/j.cmpbup.2022.100055.