Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{183871,
        author = {Radhika K R and Varadaraj R},
        title = {Enabling Secure Intelligent Networks with Cloud-Assisted Privacy-Preserving Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {3297-3302},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183871},
        abstract = {The proliferation of intelligent networks and edge computing has created unprecedented opportunities for real-time data analytics while simultaneously raising critical privacy and security concerns. Traditional centralized machine learning approaches often require raw data transmission to cloud servers, creating vulnerabilities and privacy risks that are unacceptable in sensitive domains such as healthcare, finance, and industrial IoT. This paper presents SecureNet-ML, a novel framework that enables secure intelligent network operations through cloud-assisted privacy-preserving machine learning techniques. Our approach integrates homomorphic encryption, differential privacy, and federated learning paradigms to create a comprehensive security architecture that maintains model accuracy while preserving data confidentiality. The framework employs advanced cryptographic protocols including secure multi-party computation (SMPC) and zero-knowledge proofs to ensure that sensitive information never leaves its originating network boundaries in plaintext form. Experimental validation across multiple network topologies demonstrates that SecureNet-ML achieves 94.2% accuracy retention compared to traditional centralized approaches while providing mathematically proven privacy guarantees. The system reduces privacy leakage by 87% and maintains computational efficiency suitable for real-time network operations with only 12% overhead in processing time. Performance analysis reveals superior scalability characteristics, supporting networks with up to 10,000 edge devices while maintaining sub-second response times for critical security decisions.},
        keywords = {Privacy-Preserving Machine Learning, Secure Networks, Cloud Computing, Homomorphic Encryption, Federated Learning, Edge Computing, Network Security},
        month = {August},
        }