Defending against Reconstruction Attack in Vertical Federated Learning
arXiv:2107.09898
Abstract
Recently researchers have studied input leakage problems in Federated Learning (FL) where a malicious party can reconstruct sensitive training inputs provided by users from shared gradient. It raises concerns about FL since input leakage contradicts the privacy-preserving intention of using FL. Despite a relatively rich literature on attacks and defenses of input reconstruction in Horizontal FL, input leakage and protection in vertical FL starts to draw researcher's attention recently. In this paper, we study how to defend against input leakage attacks in Vertical FL. We design an adversarial training-based framework that contains three modules: adversarial reconstruction, noise regularization, and distance correlation minimization. Those modules can not only be employed individually but also applied together since they are independent to each other. Through extensive experiments on a large-scale industrial online advertising dataset, we show our framework is effective in protecting input privacy while retaining the model utility.
arXiv commentAccepted to International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2021 (FL-ICML'21)
References in corpus (8)
- Deep Learning with Differential Privacy
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
- A fast algorithm for computing distance correlation
- Learning Anonymized Representations with Adversarial Neural Networks
- No Peek: A Survey of private distributed deep learning
- See through Gradients: Image Batch Recovery via GradInversion
- A Review of Homomorphic Encryption Libraries for Secure Computation