Enhancing UPI Security Using Deep Learning Based Voice Authentication Systems
Keywords:
Speaker Identification, UPI, Deep Learning, Voice Authentication, Convolutional Neural Networks, Fast Fourier TransformAbstract
The identity of a person can be determined based on their voice, through the process of speaker identification. It can be used to improve the security of the United Payments Interface (UPI) framework. The process involves capturing and analyzing the acoustic features of the user’s speech and comparing them to certain voice profiles that are stored in a database to find a match. Once a match is found the transaction can proceed smoothly. A model is built using the Fast Fourier Transform (FFT) and a 1-D CNN and it shows 98.46% accuracy on the data provided to it from the beginning and 98% on the validation data. This model is then compared with other existing models using different methods to obtain important attributes like Mel Spectrogram and MFCC. A process to integrate the model into the UPI ecosystem is successfully developed. This involves designing a protocol and developing an Application Programming Interface (API) for integration with UPI and Security Layering for additional threats. This paper addresses the current security concerns as well as paving the way for further research to improve security in the UPI ecosystem.
Downloads
References
Singh, Nilu. Automatic speaker recognition: current approaches and progress in the last six decades. Global Journal of Enterprise Information System 9.3, 2017, pp. 45-52.
Shayamunda, C., Ramotsoela, T. D., and Hancke, G. P. Biometric Authentication System for Industrial Applications using Speaker Recognition. The 46th Annual Conference of the IEEE Industrial Electronics Society, Industrial Electronics Society (IECON), 2020, pp. 4459–4464.
Mohd Hanifa, R., Isa, K., and Mohamad, S. A review on speaker recognition: Technology and challenges. Computers and Electrical Engineering, 2021.
Lakshmi, K. K., Gupta, H., and Ranjan, J. UPI Based Mobile Banking Applications – Security Analysis and Enhancements. 2019 Amity International Conference on Artificial Intelligence (AICAI), 2019, pp. 1– 6.
Madwanna, Y., Khadse, M., and Chandavarkar, B. R. Security Issues of Unified Payments Interface and Challenges: Case Study. ICSCCC 2021 - International Conference on Secure Cyber Computing and Communications, 2021, pp. 150-154.
Thimmaraja Yadava, G., Nagaraja, B.G. and Raghudathesh, G.P. Real-Time Automatic Continuous Speech Recognition System for Kannada Language/Dialects. Wireless Pers Commun, 2024.
Gupta, P., Patil, H.A. and Guido, R.C. Vulnerability issues in Automatic Speaker Verification (ASV) systems. J AUDIO SPEECH MUSIC PROC. 2024, 10, 2024.
Balakrishnan, M. The Unified Payment Interface and the growth of digital payments in India: An analysis. Journal of Payments Strategy & Systems, 17(3), 2023, pp. 250–270.
Popa, D., & Simion, E. Enhancing security by combining biometrics and cryptography. 2017 9th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Electronics, Computers and Artificial Intelligence (ECAI), 2017, pp. 1–7.
Khan, S. A., & Naaz, S. Comparative Analysis of Finger Vein, Iris and Human Body Odor as Biometric Approach in Cyber Security System. 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), 2020, pp. 525–530.
Vassilev, V. et al. Two-factor authentication for voice assistance in digital banking using public cloud services. Proceedings of the Confluence 2020 - 10th International Conference on Cloud Computing, Data Science and Engineering, 2020, pp. 404-409.
Yerramreddy, D. R. et al. Speaker Identification Using MFCC Feature Extraction: A Comparative Study Using GMM, CNN, RNN, KNN and Random Forest Classifier. 2023 Second International Conference on Trends in Electrical, Electronics, and Computer Engineering (TEECCON), 2023, pp. 287–292.
Prachi, N. N. et al. Deep Learning Based Speaker Recognition System with CNN and LSTM Techniques. 2022 Interdisciplinary Research in Technology and Management (IRTM), Technology and Management (IRTM), 2022 Interdisciplinary Research In, 2022, pp. 1–6.
Barhoush, M., Hallawa, A., and Schmeink, A. Robust Automatic Speaker Identification System Using Shuffled MFCC Features. 2021 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT), 2021, pp.1–6.
Jaffino, G., Raman, R., and Jose, J. P. Improved Speaker Identification System Based on MFCC and DMFCC Feature Extraction Technique. 2021 Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT), 2021, pp. 1– 5.
Singh, M. K. A text independent speaker identification system using ANN, RNN, and CNN classification technique. Multimedia Tools and Applications: An International Journal, 2023, pp. 1–13.
Shihab, M. S. H. et al. A Hybrid GRU-CNN Feature Extraction Technique for Speaker Identification. 2020 23rd International Conference on Computer and Information Technology (ICCIT), 2020, pp. 1–6.
Khekare, Ganesh, Pushpneel Verma, and Seema Raut. "The Smart Accident Predictor System using Internet of Things." Cloud IoT. Chapman and Hall/CRC, 2022. 163-175.
Ganesh Khekare, K. Pavan Kumar, Kundeti Naga Prasanthi, Sanjiv Rao Godla, Venubabu Rachapudi, Mohammed Saleh Al Ansari and Yousef A. Baker El-Ebiary, “Optimizing Network Security and Performance Through the Integration of Hybrid GAN-RNN Models in SDN-based Access Control and Traffic Engineering” International Journal of Advanced Computer Science and Applications(IJACSA), 14(12), 2023. http://dx.doi.org/10.14569/IJACSA.2023.0141262
G. Khekare, S. Gambhir, I. S. Abdulrahman, C. M. S. Kumar and V. Tripathi, "D2D Network: Implementation of Blockchain Based Equitable Cognitive Resource Sharing System," 2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), Greater Noida, India, 2023, pp. 908-912, doi: 10.1109/ICACITE57410.2023.10182834.
G. Khekare and Midhunchakkravarthy, "Smart Image Recognition System for The Visually Impaired People," 2023 International Conference on Energy, Materials and Communication Engineering (ICEMCE), Madurai, India, 2023, pp. 1-6, doi: 10.1109/ICEMCE57940.2023.10434130.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.