Ensemble Federated Adversarial Training with Non-IID data

10/26/2021
by   Shuang Luo, et al.
0

Despite federated learning endows distributed clients with a cooperative training mode under the premise of protecting data privacy and security, the clients are still vulnerable when encountering adversarial samples due to the lack of robustness. The adversarial samples can confuse and cheat the client models to achieve malicious purposes via injecting elaborate noise into normal input. In this paper, we introduce a novel Ensemble Federated Adversarial Training Method, termed as EFAT, that enables an efficacious and robust coupled training mechanism. Our core idea is to enhance the diversity of adversarial examples through expanding training data with different disturbances generated from other participated clients, which helps adversarial training perform well in Non-IID settings. Experimental results on different Non-IID situations, including feature distribution skew and label distribution skew, show that our proposed method achieves promising results compared with solely combining federated learning with adversarial approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/01/2023

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning

Privacy and security concerns in real-world applications have led to the...
research
12/03/2020

FAT: Federated Adversarial Training

Federated learning (FL) is one of the most important paradigms addressin...
research
12/20/2021

Certified Federated Adversarial Training

In federated learning (FL), robust aggregation schemes have been develop...
research
09/17/2022

pFedDef: Defending Grey-Box Attacks for Personalized Federated Learning

Personalized federated learning allows for clients in a distributed syst...
research
06/16/2022

Using adversarial images to improve outcomes of federated learning for non-IID data

One of the important problems in federated learning is how to deal with ...
research
06/05/2022

Federated Adversarial Training with Transformers

Federated learning (FL) has emerged to enable global model training over...
research
08/08/2023

Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learning

The main premise of federated learning is that machine learning model up...

Please sign up or login with your details

Forgot password? Click here to reset