Privacy-Preserving Federated Learning on Partitioned Attributes

Abstract

Real-world data is usually segmented by attributes and distributed across different parties. Federated learning empowers collaborative training without exposing local data or models. As we demonstrate through designed attacks, even with a small proportion of corrupted data, an adversary can accurately infer the input attributes. We introduce an adversarial learning based procedure which tunes a local model to release privacy-preserving intermediate representations. To alleviate the accuracy decline, we propose a defense method based on the forward-backward splitting algorithm, which respectively deals with the accuracy loss and privacy loss in the forward and backward gradient descent steps, achieving the two objectives simultaneously. Extensive experiments on a variety of datasets have shown that our defense significantly mitigates privacy leakage with negligible impact on the federated learning task.

References in corpus (10)

• Federated Learning: Strategies for Improving Communication Efficiency
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• How To Backdoor Federated Learning
• Differentially Private Federated Learning: A Client Level Perspective
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• Exploring Models and Data for Image Question Answering
• Inverting Gradients -- How easy is it to break privacy in federated learning?
• A Field Guide to Forward-Backward Splitting with a FASTA Implementation
• SecureBoost: A Lossless Federated Learning Framework