mlsanityData to 7 Oct 2026

Data Poisoning Attacks Against Federated Learning Systems

arXiv 2007.08432 ↗First posted 16 Jul 2020cs.LG cs.CR stat.MLcited by 266

Not on the map. Why?

Cited by 32 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the distributed nature of FL gives rise to new threats caused by potentially malicious participants. In this paper, we study targeted data poisoning attacks against FL systems in which a malicious subset of the participants aim to poison the global model by sending model updates derived from mislabeled data. We first demonstrate that such data poisoning attacks can cause substantial drops in classification accuracy and recall, even with a small percentage of malicious participants. We additionally show that the attacks can be targeted, i.e., they have a large negative impact only on classes that are under attack. We also study attack longevity in early/late round training, the impact of malicious participant availability, and the relationships between the two. Finally, we propose a defense strategy that can help identify malicious participants in FL to circumvent poisoning attacks, and demonstrate its effectiveness.

Key facts. Cited by 266 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 36; 2023: 52; 2024: 66; 2025: 54; 2026: 24.

266 papers.

Sort:

By area:

  1. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  2. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  3. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  4. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  5. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  6. 2024Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Surveycited by 86
  7. 2021Federated Learning: Opportunities and Challengescited by 83
  8. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
  9. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 65
  10. 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
  11. 2025Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attackscited by 49
  12. 2024Byzantine-Robust Decentralized Federated Learningcited by 47
38 more
  1. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  2. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  3. 2021Emerging Trends in Federated Learning: From Model Fusion to Federated X Learningcited by 35
  4. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  5. 2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 29
  6. 2022FLCert: Provably Secure Federated Learning against Poisoning Attackscited by 29
  7. 2022Amplifying Membership Exposure via Data Poisoningcited by 29
  8. 2023Integration of Large Language Models and Federated Learningcited by 28
  9. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challengescited by 26
  10. 2023Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teachercited by 25
  11. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  12. 2021RoFL: Robustness of Secure Federated Learningcited by 23
  13. 2021Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errorscited by 23
  14. 2021Robust Training in High Dimensions via Block Coordinate Geometric Median Descentcited by 20
  15. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  16. 2025Data Poisoning in Deep Learning: A Surveycited by 20
  17. 2023FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMscited by 19
  18. 2024Advances in APPFL: A Comprehensive and Extensible Federated Learning Frameworkcited by 19
  19. 2021Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligencecited by 18
  20. 2024Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Modelscited by 18
  21. 2022How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?cited by 17
  22. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  23. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  24. 2022Defending against the Label-flipping Attack in Federated Learningcited by 16
  25. 2023Revisiting Personalized Federated Learning: Robustness Against Backdoor Attackscited by 16
  26. 2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
  27. 2021Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthinesscited by 15
  28. 2021Learning-to-learn non-convex piecewise-Lipschitz functionscited by 15
  29. 2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
  30. 2023Fusion of Global and Local Knowledge for Personalized Federated Learningcited by 14
  31. 2023Fast Adversarial Training with Smooth Convergencecited by 14
  32. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 14
  33. 2021Get a Model! Model Hijacking Attack Against Machine Learning Modelscited by 13
  34. 2022Machine Learning with Confidential Computing: A Systematization of Knowledgecited by 13
  35. 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 13
  36. 2025Do We Really Need to Design New Byzantine-robust Aggregation Rules?cited by 13
  37. 2021Untargeted Poisoning Attack Detection in Federated Learning via Behavior Attestationcited by 12
  38. 2022Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestrationcited by 12

50 most cited of 266 All 266 (JSON)