Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiao, Yu, Adhikary, Apurba, Le, Huy Q., Huh, Eui-Nam, Han, Zhu, Hong, Choong Seon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910907242643456
author Qiao, Yu
Adhikary, Apurba
Le, Huy Q.
Huh, Eui-Nam
Han, Zhu
Hong, Choong Seon
author_facet Qiao, Yu
Adhikary, Apurba
Le, Huy Q.
Huh, Eui-Nam
Han, Zhu
Hong, Choong Seon
contents Federated learning (FL) has gained significant attention for enabling decentralized training on edge networks without exposing raw data. However, FL models remain susceptible to adversarial attacks and performance degradation in non-IID data settings, thus posing challenges to both robustness and accuracy. This paper aims to achieve communication-efficient adversarial federated learning (AFL) by leveraging a pre-trained model to enhance both robustness and accuracy under adversarial attacks and non-IID challenges in AFL. By leveraging the knowledge from a pre-trained model for both clean and adversarial images, we propose a pre-trained model-guided adversarial federated learning (PM-AFL) framework. This framework integrates vanilla and adversarial mixture knowledge distillation to effectively balance accuracy and robustness while promoting local models to learn from diverse data. Specifically, for clean accuracy, we adopt a dual distillation strategy where the class probabilities of randomly paired images, and their blended versions are aligned between the teacher model and the local models. For adversarial robustness, we employ a similar distillation approach but replace clean samples on the local side with adversarial examples. Moreover, by considering the bias between local and global models, we also incorporate a consistency regularization term to ensure that local adversarial predictions stay aligned with their corresponding global clean ones. These strategies collectively enable local models to absorb diverse knowledge from the teacher model while maintaining close alignment with the global model, thereby mitigating overfitting to local optima and enhancing the generalization of the global model. Experiments demonstrate that the PM-AFL-based framework not only significantly outperforms other methods but also maintains communication efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15257
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence
Qiao, Yu
Adhikary, Apurba
Le, Huy Q.
Huh, Eui-Nam
Han, Zhu
Hong, Choong Seon
Computer Vision and Pattern Recognition
Federated learning (FL) has gained significant attention for enabling decentralized training on edge networks without exposing raw data. However, FL models remain susceptible to adversarial attacks and performance degradation in non-IID data settings, thus posing challenges to both robustness and accuracy. This paper aims to achieve communication-efficient adversarial federated learning (AFL) by leveraging a pre-trained model to enhance both robustness and accuracy under adversarial attacks and non-IID challenges in AFL. By leveraging the knowledge from a pre-trained model for both clean and adversarial images, we propose a pre-trained model-guided adversarial federated learning (PM-AFL) framework. This framework integrates vanilla and adversarial mixture knowledge distillation to effectively balance accuracy and robustness while promoting local models to learn from diverse data. Specifically, for clean accuracy, we adopt a dual distillation strategy where the class probabilities of randomly paired images, and their blended versions are aligned between the teacher model and the local models. For adversarial robustness, we employ a similar distillation approach but replace clean samples on the local side with adversarial examples. Moreover, by considering the bias between local and global models, we also incorporate a consistency regularization term to ensure that local adversarial predictions stay aligned with their corresponding global clean ones. These strategies collectively enable local models to absorb diverse knowledge from the teacher model while maintaining close alignment with the global model, thereby mitigating overfitting to local optima and enhancing the generalization of the global model. Experiments demonstrate that the PM-AFL-based framework not only significantly outperforms other methods but also maintains communication efficiency.
title Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.15257