mlsanityData to 14 Oct 2026

Client-Side Patching against Backdoor Attacks in Federated Learning

arXiv 2412.10605 ↗First posted 13 Dec 2024cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning is a versatile framework for training models in decentralized environments. However, the trust placed in clients makes federated learning vulnerable to backdoor attacks launched by malicious participants. While many defenses have been proposed, they often fail short when facing heterogeneous data distributions among participating clients. In this paper, we propose a novel defense mechanism for federated learning systems designed to mitigate backdoor attacks on the clients-side. Our approach leverages adversarial learning techniques and model patching to neutralize the impact of backdoor attacks. Through extensive experiments on the MNIST and Fashion-MNIST datasets, we demonstrate that our defense effectively reduces backdoor accuracy, outperforming existing state-of-the-art defenses, such as LFighter, FLAME, and RoseAgg, in i.i.d. and non-i.i.d. scenarios, while maintaining competitive or superior accuracy on clean data.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 38 references that are in the map. First posted on arXiv 13 Dec 2024.

Builds on

18 of 38 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2018How To Backdoor Federated Learningcited by 765
  5. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  6. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  7. 2020Input-Aware Dynamic Backdoor Attackcited by 313
  8. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  9. 2019Can You Really Backdoor Federated Learning?cited by 255
  10. 2021Adaptive Machine Unlearningcited by 176
  11. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  12. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
6 more
  1. 2022Federated Unlearning with Knowledge Distillationcited by 73
  2. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  3. 2023Federated Learning for Connected and Automated Vehicles: A Survey of Existing Approaches and Challengescited by 40
  4. 2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 31
  5. 2022CrowdGuard: Federated Backdoor Detection in Federated Learningcited by 27
  6. 2024Celtibero: Robust Layered Aggregation for Federated Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023On the Vulnerability of Backdoor Defenses for Federated Learning
  2. 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
  3. 2022Invariant Aggregator for Defending against Federated Backdoor Attacks
  4. 2025FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
  5. 2024Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
  6. 2022Towards a Defense Against Federated Backdoor Attacks Under Continuous Training
  7. 2023FedDefender: Backdoor Attack Defense in Federated Learning
  8. 2025BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning