DeepAI
Log In Sign Up

Privacy-Preserving Federated Learning on Partitioned Attributes

04/29/2021
by   Shuang Zhang, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/01/2022

Defense Against Gradient Leakage Attacks via Learning to Obscure Data

Federated learning is considered as an effective privacy-preserving lear...
10/05/2020

Towards Generalized and Distributed Privacy-Preserving Representation Learning

We study the problem of learning data representations that are private y...
10/18/2019

Federated Generative Privacy

In this paper, we propose FedGP, a framework for privacy-preserving data...
08/14/2020

Privacy-Preserving Asynchronous Federated Learning Algorithms for Multi-Party Vertically Collaborative Learning

The privacy-preserving federated learning for vertically partitioned dat...
05/23/2022

Privacy-preserving Data Filtering in Federated Learning Using Influence Approximation

Federated Learning by nature is susceptible to low-quality, corrupted, o...
07/07/2020

Backdoor attacks and defenses in feature-partitioned collaborative learning

Since there are multiple parties in collaborative learning, malicious pa...
01/08/2022

Attacking Vertical Collaborative Learning System Using Adversarial Dominating Inputs

Vertical collaborative learning system also known as vertical federated ...