• Home
  • Search
  • Resisting Distributed Backdoor Attacks in Federated Learning: A Dynamic Norm Clipping Approach
  • Cite Icon19
  • https://doi.org/10.1109/bigdata52589.2021.9671910Copy DOI Icon

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

  • Dec 15, 2021
  • Yifan Guo +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

With the advance in artificial intelligence and high-dimensional data analysis, federated learning (FL) has emerged to allow distributed data providers to collaboratively learn without direct access to local sensitive data. However, limiting access to individual provider’s data inevitably incurs security issues. For instance, backdoor attacks, one of the most popular data poisoning attacks in FL, severely threaten the integrity and utility of the FL system. In particular, backdoor attacks launched by multiple collusive attackers, i.e., distributed backdoor attacks, can achieve high attack success rates and are hard to detect. Existing defensive approaches, like model inspection or model sanitization, often require to access a portion of local training data, which renders them inapplicable to the FL scenarios. Recently, the norm clipping approach is developed to effectively defend against distributed backdoor attacks in FL, which does not rely on local training data. However, we discover that adversaries can still bypass this defense scheme through robust training due to its unchanged norm clipping threshold. In this paper, we propose a novel defense scheme to resist distributed backdoor attacks in FL. Particularly, we first identify that the main reason for the failure of the norm clipping scheme is its fixed threshold in the training process, which cannot capture the dynamic nature of benign local updates during the global model’s convergence. Motivated by it, we devise a novel defense mechanism to dynamically adjust the norm clipping threshold of local updates. Moreover, we provide the convergence analysis of our defense scheme. By evaluating it on four non-IID public datasets, we observe that our defense scheme effectively can resist distributed backdoor attacks and ensure the global model’s convergence. Noticeably, our scheme reduces the attack success rates by 84.23% on average compared with existing defense schemes.

Similar Papers
  • Book Chapter
  • Citations160

CONTRA: Defending Against Poisoning Attacks in Federated Learning

  • Jan 01, 2021
  • Sana Awan +2
  • Research Article
  • Citations3

SARS: A Personalized Federated Learning Framework Towards Fairness and Robustness against Backdoor Attacks

  • Nov 21, 2024
  • Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
  • Weibin Zhang +4
  • Research Article
  • Citations4

G 2 uardFL: Safeguarding Federated Learning Against Backdoor Attacks via Attributed Client Graph Clustering

  • Jan 01, 2026
  • IEEE Transactions on Information Forensics and Security
  • Hao Yu +7
  • Research Article
  • Citations18

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

  • Aug 04, 2023
  • Computers & Security
  • Yongkang Wang +2
  • Research Article
  • Citations46

Defense against backdoor attack in federated learning

  • Jun 28, 2022
  • Computers & Security
  • Shiwei Lu +3
  • Conference Article

Robust Federated Learning via Relevant Model Slicing

  • Feb 21, 2025
  • Xiaojie Mo +4
  • 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
  • Citations12

Towards Practical Backdoor Attacks on Federated Learning Systems

  • Nov 01, 2024
  • IEEE Transactions on Dependable and Secure Computing
  • Chenghui Shi +8
  • PDF
  • Research Article
  • Citations1

ARMOR: Differential Model Distribution for Adversarially Robust Federated Learning

  • Feb 07, 2023
  • Electronics
  • Yanting Zhang +5
  • Research Article
  • Citations6

Robust Federated Learning Against Data Poisoning Attacks: Prevention and Detection of Attacked Nodes

  • Jul 25, 2025
  • Electronics
  • Pretom Roy Ovi +1
  • Research Article

Differential Private Defense Against Backdoor Attacks in Federated Learning

  • Aug 28, 2024
  • Frontiers in Computing and Intelligent Systems
  • Lu Miao +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
  • Conference Article
  • Citations18

Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design

  • Dec 01, 2021
  • Zhe Zhang +6
  • Research Article
  • Citations67

Coordinated Backdoor Attacks against Federated Learning with Model-Dependent Triggers

  • Jan 01, 2022
  • IEEE Network
  • Xueluan Gong +5
  • Conference Article
  • Citations7

Coalition Formation Game in the Cross-Silo Federated Learning System

  • Oct 01, 2022
  • Suhan Jiang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.