• Home
  • Search
  • Differential Private Defense Against Backdoor Attacks in Federated Learning
  • https://doi.org/10.54097/dyt1nn60Copy DOI Icon

Differential Private Defense Against Backdoor Attacks in Federated Learning

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Federated learning has been applied in a wide variety of applications, in which clients upload their local updates instead of providing their datasets to jointly train a global model. However, the training process of federated learning is vulnerable to adversarial attacks (e.g., backdoor attack) in presence of malicious clients. Previous works showed that differential privacy (DP) can be used to defend against backdoor attacks, at the cost of vastly losing model utility. In this work, we study two kinds of backdoor attacks and propose a method based on differential privacy, called Clip Norm Decay (CND) to defend against them, which maintains utility when defending against backdoor attacks with DP. CND decreases the clipping threshold of model updates through the whole training process to reduce the injected noise. Empirical results show that CND can substantially enhance the accuracy of the main task. In particular, CND bounds the norm of malicious updates by adaptively setting the appropriate thresholds according to the current model updates. Empirical results show that CND can substantially enhance the accuracy of the main task when defending against backdoor attacks. Moreover, extensive experiments demonstrate that our method performs better defense than the original DP, further reducing the attack success rate, even in a strong assumption of threat model. Additional experiments about property inference attack indicate that CND also maintains utility when defending against privacy attacks and does not weaken the privacy preservation of DP.

Similar Papers
  • Conference Article
  • Citations19

Against Backdoor Attacks In Federated Learning With Differential Privacy

  • May 23, 2022
  • Lu Miao +4
  • Research Article
  • Citations12

Towards Practical Backdoor Attacks on Federated Learning Systems

  • Nov 01, 2024
  • IEEE Transactions on Dependable and Secure Computing
  • Chenghui Shi +8
  • Research Article
  • Citations2

IPCADP‐Equalizer: An Improved Multibalance Privacy Preservation Scheme against Backdoor Attacks in Federated Learning

  • Jan 01, 2023
  • International Journal of Intelligent Systems
  • Wenjuan Lian +4
  • Research Article
  • Citations1

XMAM:X-raying models with a matrix to reveal backdoor attacks for federated learning

  • Jan 24, 2023
  • Digital Communications and Networks
  • Jianyi Zhang +5
  • Research Article
  • Citations101

Backdoor attacks and defenses in federated learning: Survey, challenges and future research directions

  • Oct 05, 2023
  • Engineering Applications of Artificial Intelligence
  • Thuy Dung Nguyen +5
  • Conference Article
  • Citations19

Resisting Distributed Backdoor Attacks in Federated Learning: A Dynamic Norm Clipping Approach

  • Dec 15, 2021
  • Yifan Guo +4
  • Research Article
  • Citations18

SCFL: Mitigating backdoor attacks in federated learning based on SVD and clustering

  • Aug 04, 2023
  • Computers & Security
  • Yongkang Wang +2
  • Conference Article
  • Citations140

Local and Central Differential Privacy for Robustness and Privacy in Federated Learning

  • Jan 01, 2022
  • Mohammad Naseri +2
  • Conference Article

Robust Federated Learning via Relevant Model Slicing

  • Feb 21, 2025
  • Xiaojie Mo +4
  • Research Article
  • Citations13

A Comparative Study of Privacy-Preserving Techniques in Federated Learning: A Performance and Security Analysis

  • Mar 18, 2025
  • Information
  • Eman Shalabi +3
  • Research Article
  • Citations7

FREPD: A Robust Federated Learning Framework on Variational Autoencoder

  • Jan 01, 2021
  • Computer Systems Science and Engineering
  • Zhipin Gu +5
  • Research Article
  • Citations7

Facilitating Early-Stage Backdoor Attacks in Federated Learning With Whole Population Distribution Inference

  • Jun 15, 2023
  • IEEE Internet of Things Journal
  • Tian Liu +2
  • Research Article
  • Citations1

FinBack: Infiltrating Backdoors into Gradient Compressors on Federated Learning

  • Jan 01, 2025
  • IEEE Transactions on Information Forensics and Security
  • Xiangyun Tang +7
  • Research Article
  • Citations40

Backdoor attack and defense in federated generative adversarial network-based medical image synthesis.

  • Dec 01, 2023
  • Medical Image Analysis
  • Ruinan Jin +1
  • Research Article
  • Citations12

High-accuracy low-cost privacy-preserving federated learning in IoT systems via adaptive perturbation

  • Sep 01, 2022
  • Journal of Information Security and Applications
  • Tian Liu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.