CAFE: Catastrophic Data Leakage in Vertical Federated Learning

Abstract

Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate data recovery is often viewed as a promising defense strategy against data leakage. In this paper, we revisit this defense premise and propose an advanced data leakage attack with theoretical justification to efficiently recover batch data from the shared aggregated gradients. We name our proposed method as catastrophic data leakage in vertical federated learning (CAFE). Comparing to existing data leakage attacks, our extensive experimental results on vertical FL settings demonstrate the effectiveness of CAFE to perform large-batch data leakage attack with improved data recovery quality. We also propose a practical countermeasure to mitigate CAFE. Our results suggest that private data participated in standard FL, especially the vertical case, have a high risk of being leaked from the training gradients. Our analysis implies unprecedented and practical data leakage risks in those learning settings. The code of our work is available at https://github.com/DeRafael/CAFE.

References in corpus (10)

• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• How To Backdoor Federated Learning
• Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization
• iDLG: Improved Deep Leakage from Gradients
• FedML: A Research Library and Benchmark for Federated Machine Learning
• SecureBoost: A Lossless Federated Learning Framework
• A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
• VAFL: a Method of Vertical Asynchronous Federated Learning
• SAPAG: A Self-Adaptive Privacy Attack From Gradients