Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms

TL;DR

This survey reviews the integration of federated and transfer learning, focusing on security challenges and defense mechanisms to protect privacy and system performance in distributed machine learning.

Contribution

It provides a comprehensive overview of security vulnerabilities and defense strategies in federated and transfer learning systems.

Findings

Identifies key security vulnerabilities in federated and transfer learning.

Summarizes existing defense mechanisms against adversaries.

Highlights open challenges and future research directions.

Abstract

The advent of federated learning has facilitated large-scale data exchange amongst machine learning models while maintaining privacy. Despite its brief history, federated learning is rapidly evolving to make wider use more practical. One of the most significant advancements in this domain is the incorporation of transfer learning into federated learning, which overcomes fundamental constraints of primary federated learning, particularly in terms of security. This chapter performs a comprehensive survey on the intersection of federated and transfer learning from a security point of view. The main goal of this study is to uncover potential vulnerabilities and defense mechanisms that might compromise the privacy and performance of systems that use federated and transfer learning.