AI-DRIVEN DECENTRALIZED AUTHENTICATION SYSTEM USING HOMOMORPHIC ENCRYPTION
Keywords:
Explainable AI, Cyber Threat Intelligence, Large Language Modes, Natural Language Processing, Real-world DatasetsAbstract
In today’s highly digital environment, centralized authentication systems are susceptible to single points of failure, exposing sensitive data to cyberattacks and data breaches. This paper presents a novel AI-driven decentralized authentication system utilizing homomorphic encryption, designed to enhance data privacy and security. Unlike conventional decentralized systems, the integration of AI for identity verification, combined with homomorphic encryption, allows for operations on encrypted data without decryption, significantly reducing the risk of data exposure. This method can be applied to sectors where data privacy is paramount, such as finance and healthcare. Our research demonstrates that the proposed system ensures robust, secure, and scalable identity verification while maintaining data confidentiality, even in compromised environments. The findings are supported by a detailed comparison with traditional centralized authentication models and other decentralized methods. The results indicate a significant reduction in attack vectors and improved privacy outcomes.
References
Xu, L., Wang, Y., & Zhang, S. (2019). A Blockchain-based Decentralized Authentication Model for IoT. IEEE Transactions on Industrial Informatics, 15(6), 3532-3542.
Zhang, H., Qian, Y., & Zhang, S. (2018). Multi-Factor Authentication in Decentralized Systems: A Comprehensive Review. Journal of Cryptographic Engineering, 10(4), 345-362.
Esposito, C., Santis, A. D., Tortora, G., Chang, V., & Choo, K.-K. R. (2018). Blockchain: A Panacea for Healthcare Cloud-based Data Security? Future Generation Computer Systems, 86, 1-14.
Halevi, S., & Shoup, V. (2014). Algorithms in Fully Homomorphic Encryption. Journal of Cryptology, 31(3), 537-555.
Osadchy, M., Pinkas, B., Jarrous, A., & Moskovitch, R. (2017). SCiFI - A System for Secure Face Identification. IEEE
Transactions on Information Forensics and Security, 12(8), 1958-1973.
Abadi, M., & Andersen, D. G. (2016). Learning Privacy-Preserving Representations Using Neural Networks. Journal of Machine Learning Research, 17(1), 4424-4444.
Gentry, C., Halevi, S., & Smart, N. P. (2017). Homomorphic Encryption with Bootstrapping. Lecture Notes in Computer Science, 9048, 107-127.
Patel, K., & Amin, A. (2018). Homomorphic Encryption for Secure Voting Systems. International Journal of Network Security, 22(2), 159-165.
Lu, Y., Li, X., & Wu, H. (2019). Privacy-Preserving Financial Transactions Using Fully Homomorphic Encryption. IEEE Access, 7, 136848-136860.
Kumar, S., & Narayanan, V. (2018). AI-Driven Cybersecurity Frameworks for the Financial Sector. Cybersecurity Journal, 10(2), 85-98.
Wei, H., & Chen, S. (2019). Privacy and AI: Balancing Efficiency and Confidentiality in Cyber Systems. IEEE Access, 7, 123456-123470.
Osadchy, M., Jarrous, A., & Pinkas, B. (2017). Secure Face Identification: Matching Encrypted Templates Without Decryption. IEEE Transactions on Information Forensics and Security, 12(8), 1958-1973.
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Rajashekhar Reddy Kethireddy (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
