A Framework for Evaluating Gradient Leakage Attacks in Federated Learning

04/22/2020
by   Wenqi Wei, et al.
5

Federated learning (FL) is an emerging distributed machine learning framework for collaborative model training with a network of clients (edge devices). FL offers default client privacy by allowing clients to keep their sensitive data on local devices and to only share local training parameter updates with the federated server. However, recent studies have shown that even sharing local parameter updates from a client to the federated server may be susceptible to gradient leakage attacks and intrude the client privacy regarding its training data. In this paper, we present a principled framework for evaluating and comparing different forms of client privacy leakage attacks. We provide formal and experimental analysis to show how adversaries can reconstruct the private local training data by simply analyzing the shared parameter update from local training (e.g., local gradient or weight update vector). Our framework can measure, evaluate, and analyze the adverse effects and cost of client privacy leakage attacks under different configurations of federated learning and different settings of the attack algorithm on four benchmark datasets. Our experiments also include some preliminary mitigation strategies to highlight the importance of providing a systematic attack evaluation framework towards an in-depth understanding of the various forms of client privacy leakage threats in federated learning and developing theoretical foundations for attack mitigation.

READ FULL TEXT

page 6

page 13

page 20

research
07/02/2021

Gradient-Leakage Resilient Federated Learning

Federated learning(FL) is an emerging distributed learning paradigm with...
research
06/08/2022

Gradient Obfuscation Gives a False Sense of Security in Federated Learning

Federated learning has been proposed as a privacy-preserving machine lea...
research
08/03/2022

How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?

Federated learning (FL) has attracted growing interest for enabling priv...
research
12/07/2021

Location Leakage in Federated Signal Maps

We consider the problem of predicting cellular network performance (sign...
research
01/01/2021

Fidel: Reconstructing Private Training Samples from Weight Updates in Federated Learning

With the increasing number of data collectors such as smartphones, immen...
research
06/24/2022

Data Leakage in Federated Averaging

Recent attacks have shown that user data can be recovered from FedSGD up...
research
06/09/2021

FedDICE: A ransomware spread detection in a distributed integrated clinical environment using federated learning and SDN based mitigation

An integrated clinical environment (ICE) enables the connection and coor...

Please sign up or login with your details

Forgot password? Click here to reset