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{177040,
        author = {Nehanshu Dave and Prakash Patel},
        title = {Toward Enhanced Machine Learning Privacy: An Adaptive Differential Privacy Methodology},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {298-302},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177040},
        abstract = {The increasing reliance on machine learning models for processing sensitive data necessitates robust privacy protection mechanisms. Differential privacy (DP) has emerged as a leading approach to ensure privacy-preserving data analysis by adding controlled noise to datasets and model parameters. This paper explores various DP techniques in machine learning, evaluates their effectiveness, and proposes an enhanced approach to balance privacy and model utility.},
        keywords = {Differential Privacy, Machine Learning, Privacy-Preserving Models, DP-SGD, Privacy Budgets},
        month = {April},
        }