FAT: Federated Adversarial Training

12/03/2020
by   Giulio Zizzo, et al.
0

Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has emerged, so far, as the most promising approach against evasion threats on ML models. In this paper, we take the first known steps towards federated adversarial training (FAT) combining both methods to reduce the threat of evasion during inference while preserving the data privacy during training. We investigate the effectiveness of the FAT protocol for idealised federated settings using MNIST, Fashion-MNIST, and CIFAR10, and provide first insights on stabilising the training on the LEAF benchmark dataset which specifically emulates a federated learning environment. We identify challenges with this natural extension of adversarial training with regards to achieved adversarial robustness and further examine the idealised settings in the presence of clients undermining model convergence. We find that Trimmed Mean and Bulyan defences can be compromised and we were able to subvert Krum with a novel distillation based attack which presents an apparently "robust" model to the defender while in fact the model fails to provide robustness against simple attack modifications.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2021

Ensemble Federated Adversarial Training with Non-IID data

Despite federated learning endows distributed clients with a cooperative...
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
12/10/2021

SoK: On the Security Privacy in Federated Learning

Advances in Machine Learning (ML) and its wide range of applications boo...
research
12/20/2021

Certified Federated Adversarial Training

In federated learning (FL), robust aggregation schemes have been develop...
research
11/10/2022

Robust Smart Home Face Recognition under Starving Federated Data

Over the past few years, the field of adversarial attack received numero...
research
03/23/2023

Adversarial Robustness and Feature Impact Analysis for Driver Drowsiness Detection

Drowsy driving is a major cause of road accidents, but drivers are dismi...
research
04/14/2020

Secure Federated Learning in 5G Mobile Networks

Machine Learning (ML) is an important enabler for optimizing, securing a...

Please sign up or login with your details

Forgot password? Click here to reset