mlsanityData to 14 Oct 2026

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning

arXiv 2404.17617 ↗First posted 26 Apr 2024cs.CR cs.AI cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of this weakened backdoor effect, called attack persistence. Given that research to improve this performance has not been widely noted,we propose a Full Combination Backdoor Attack (FCBA) method. It aggregates more combined trigger information for a more complete backdoor pattern in the global model. Trained backdoored global model is more resilient to benign updates, leading to a higher attack success rate on the test set. We test on three datasets and evaluate with two models across various settings. FCBA's persistence outperforms SOTA federated learning backdoor attacks. On GTSRB, postattack 120 rounds, our attack success rate rose over 50% from baseline. The core code of our method is available at https://github.com/PhD-TaoLiu/FCBA.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 26 Apr 2024.

Builds on

18 of 37 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Learning with Non-IID Datacited by 1,108
  4. 2019Towards Federated Learning at Scale: System Designcited by 832
  5. 2018How To Backdoor Federated Learningcited by 765
  6. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  7. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  8. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  9. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  10. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 360
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  12. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
6 more
  1. 2019Can You Really Backdoor Federated Learning?cited by 255
  2. 2019Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attackscited by 79
  3. 2018Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerancecited by 8
  4. 2022Dispersed Pixel Perturbation-based Imperceptible Backdoor Trigger for Image Classifier Modelscited by 7
  5. 2017Online Learning with Gated Linear Networkscited by 6
  6. 2022On the Permanence of Backdoors in Evolving Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 6; 2026: 6.

16 papers.

Sort:

By area:

  1. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 15
  2. 2024Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guaranteecited by 6
  3. 2026Rethinking LoRA for Privacy-Preserving Federated Learning in Large Modelscited by 5
  4. 2025Cooperative Decentralized Backdoor Attacks on Vertical Federated Learningcited by 3
  5. 2025Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learningcited by 2
  6. 2026When AI reviews science: Can we trust the referee?cited by 2
  7. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learningcited by 1
  8. 2026On Identifying Adversarial Intent Injection in AI-Native 6G Networkscited by 1
  9. 2024A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learningcited by 0
  10. 2024Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learningcited by 0
  11. 2025FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learningcited by 0
  12. 2025FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learningcited by 0
4 more
  1. 2025BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learningcited by 0
  2. 2026ADCA: Attention-Driven Multi-Party Collusion Attack in Federated Self-Supervised Learningcited by 0
  3. 2026PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learningcited by 0
  4. 2026The Power of Backdoor Absorption in Community Trainingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023On the Vulnerability of Backdoor Defenses for Federated Learning
  2. 2022Towards a Defense Against Federated Backdoor Attacks Under Continuous Training
  3. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
  4. 2022Technical Report: Assisting Backdoor Federated Learning with Whole Population Knowledge Alignment
  5. 2025SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning
  6. 2022Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning
  7. 2024Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape
  8. 2023Backdoor Federated Learning by Poisoning Backdoor-Critical Layers