FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation
It addresses privacy concerns for parties in vertical federated learning, offering an incremental improvement over existing methods.
The paper tackles privacy leakage in vertical federated learning by proposing FedPass, a framework that uses adaptive obfuscation to protect features and labels, achieving a near-optimal trade-off between privacy and model performance as validated by experiments.
Vertical federated learning (VFL) allows an active party with labeled feature to leverage auxiliary features from the passive parties to improve model performance. Concerns about the private feature and label leakage in both the training and inference phases of VFL have drawn wide research attention. In this paper, we propose a general privacy-preserving vertical federated deep learning framework called FedPass, which leverages adaptive obfuscation to protect the feature and label simultaneously. Strong privacy-preserving capabilities about private features and labels are theoretically proved (in Theorems 1 and 2). Extensive experimental result s with different datasets and network architectures also justify the superiority of FedPass against existing methods in light of its near-optimal trade-off between privacy and model performance.