Securing Insights: Safeguarding Sensitive Data in Machine Learning Through Privacy-Preserving Techniques

EasyChair Preprint no. 12042

Abstract

This paper explores the critical need for privacy-preserving techniques in machine learning to ensure the security of sensitive data. As the integration of machine learning models becomes ubiquitous in various domains, protecting confidential information is paramount. The proposed techniques discussed here aim to strike a balance between harnessing the power of data for model training and safeguarding individual privacy. From federated learning to homomorphic encryption, this paper delves into diverse methods that contribute to a robust framework for privacy preservation in machine learning.

Keyphrases: Anonymization, Data Security, differential privacy, Federated Learning, homomorphic encryption, machine learning, Model Aggregation, privacy preserving, secure multi-party computation, sensitive data

@Booklet{EasyChair:12042,
  author = {Haney Zaki},
  title = {Securing Insights: Safeguarding Sensitive Data in Machine Learning Through Privacy-Preserving Techniques},
  howpublished = {EasyChair Preprint no. 12042},

  year = {EasyChair, 2024}}