• Home
  • Search
  • Model Backdoor Attack on Federated Learning Based on Parameter Analysis
  • https://doi.org/10.1109/tdsc.2026.3664908Copy DOI Icon

Model Backdoor Attack on Federated Learning Based on Parameter Analysis

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

With the increasingly widespread application of federated learning (FL) in various fields, the issue of backdoor attacks against FL has garnered significant attention from both academia and industry. While there has been some progress in researching backdoor attacks against FL, data backdoor attacks are easily mitigated in federated environments, and model backdoor attacks are susceptible to detection by defense mechanisms. Therefore, we propose a refined backdoor attack method tailored for FL under the image classification task. Our method involves the collaborative operation of three key modules. Firstly, the parameter importance analysis module identifies parameters with minimal impact on model performance, and creates parameter importance masks to provide precise targets for subsequent operations. Subsequently, the activation difference computation module calculates the activation differences between backdoor samples and benign samples to locate trigger-sensitive parameters. Our method implants the backdoor by flipping and zeroing the precisely located layer parameters, while maintaining the model's classification performance on benign samples. Experimental results show that our method is feasible to achieve an average attack success rate more than 99% across the three victim models. This demonstrates the effectiveness of our method in FL environments and its robustness against various FL defense mechanisms.

Similar Papers
  • 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
  • Citations11

Backdoor Federated Learning-Based mmWave Beam Selection

  • Oct 01, 2022
  • IEEE Transactions on Communications
  • Zhengming Zhang +5
  • 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
  • Citations40

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

  • Dec 01, 2023
  • Medical Image Analysis
  • Ruinan Jin +1
  • Conference Article
  • Citations4

Assisting Backdoor Federated Learning with Whole Population Knowledge Alignment in Mobile Edge Computing

  • Sep 20, 2022
  • Tian Liu +2
  • Research Article
  • Citations18

RoPE: Defending against backdoor attacks in federated learning systems

  • Mar 18, 2024
  • Knowledge-Based Systems
  • Yongkang Wang +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
  • Citations12

Towards Practical Backdoor Attacks on Federated Learning Systems

  • Nov 01, 2024
  • IEEE Transactions on Dependable and Secure Computing
  • Chenghui Shi +8
  • 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
  • Conference Article
  • Citations30

FederatedReverse: A Detection and Defense Method Against Backdoor Attacks in Federated Learning

  • Jun 17, 2021
  • Chen Zhao +4
  • Research Article
  • Citations204

Defending against Backdoors in Federated Learning with Robust Learning Rate

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Mustafa Safa Ozdayi +2
  • Research Article
  • Citations2

Backdoor Two-Stream Video Models on Federated Learning

  • Sep 12, 2024
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jing Zhao +7
  • 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
  • Citations179

BaFFLe: Backdoor Detection via Feedback-based Federated Learning

  • Jul 01, 2021
  • Sebastien Andreina +3
  • Conference Article
  • Citations2

GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning

  • May 24, 2024
  • Xiaoyun Gan +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.