Quantification of the Leakage in Federated Learning

Abstract

With the growing emphasis on users' privacy, federated learning has become more and more popular. Many architectures have been raised for a better security. Most architecture work on the assumption that data's gradient could not leak information. However, some work, recently, has shown such gradients may lead to leakage of the training data. In this paper, we discuss the leakage based on a federated approximated logistic regression model and show that such gradient's leakage could leak the complete training data if all elements of the inputs are either 0 or 1.

References in corpus (2)

• Federated Learning: Strategies for Improving Communication Efficiency
• Differentially Private Federated Learning: A Client Level Perspective

Cited by in corpus (5)

• From Distributed Machine Learning to Federated Learning: A Survey
• Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
• A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
• When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control
• SoK: Training Machine Learning Models over Multiple Sources with Privacy Preservation