Privacy-Preserving Machine Learning Techniques: Balancing Utility and Data Protection

Authors

  • Ugandhar Dasi, Nikhil Singla, Rajkumar Balasubramanian, Siddhant Benadikar, Rishabh Rajesh Shanbhag

Keywords:

Differential Privacy, Federated Learning, Secure Multi-Party Computation, Banking.

Abstract

This research article provides information regarding the concerns of Privacy-Preserving Machine Learning (PPML) Techniques that includes Differential Privacy, Federated Learning, and Secure Multi-Party Computation. It is also noticed that Privacy Models are useful to achieve significant privacy and minimal loss in model accuracy. This further demonstrates that these kinds of strategies in the main application areas such as Healthcare, Banking, Internet-Of-Things (IOT), and Manufacturing, provides near-perfect privacy that can be useful while it meets minimal compromise in model accuracy. Some of the findings are enhanced data security, high accuracy of the chosen model, and ideas for future development.

Downloads

Published

2024-04-29

How to Cite

Ugandhar Dasi, Nikhil Singla, Rajkumar Balasubramanian, Siddhant Benadikar, Rishabh Rajesh Shanbhag. (2024). Privacy-Preserving Machine Learning Techniques: Balancing Utility and Data Protection. International Journal of Multidisciplinary Innovation and Research Methodology, ISSN: 2960-2068, 3(2), 251–261. Retrieved from https://ijmirm.com/index.php/ijmirm/article/view/107