mlsanityData to 14 Oct 2026

Privacy and Robustness in Federated Learning: Attacks and Defenses

arXiv 2012.06337 ↗First posted 7 Dec 2020cs.CR cs.AIcited by 166

Not on the map. Why?

Abstract (arXiv)

As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol design has been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy-preserving federated learning.

Key facts. Cited by 166 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 22; 2023: 45; 2024: 42; 2025: 30; 2026: 14.

166 papers.

Sort:

By area:

  1. 2021Towards Personalized Federated Learningcited by 464
  2. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  3. 2021DENSE: Data-Free One-Shot Federated Learningcited by 100
  4. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  5. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  6. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 85
  7. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  8. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 84
  9. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trendscited by 84
  10. 2023Federated Learning for Medical Image Analysis: A Surveycited by 78
  11. 2022Recovering Private Text in Federated Learning of Language Modelscited by 70
  12. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
38 more
  1. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 39
  2. 2024Recent Advances of Multimodal Continual Learning: A Comprehensive Surveycited by 39
  3. 2021Federated Learning for Malware Detection in IoT Devicescited by 36
  4. 2024Advances and Open Challenges in Federated Foundation Modelscited by 36
  5. 2023Towards Personalized Federated Learning via Heterogeneous Model Reassemblycited by 31
  6. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 30
  7. 2022A Survey on Federated Recommendation Systemscited by 25
  8. 2023Uncovering and Quantifying Social Biases in Code Generationcited by 25
  9. 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
  10. 2022FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentationcited by 24
  11. 2021Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfercited by 23
  12. 2023Federated Learning for Computer Visioncited by 22
  13. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  14. 2023FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregationcited by 22
  15. 2023Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learningcited by 21
  16. 2022CalFAT: Calibrated Federated Adversarial Training with Label Skewnesscited by 20
  17. 2023Delving into the Adversarial Robustness of Federated Learningcited by 19
  18. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 18
  19. 2024Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Modelscited by 18
  20. 2023Revisiting Personalized Federated Learning: Robustness Against Backdoor Attackscited by 16
  21. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 15
  22. 2022Hypernetwork-based Personalized Federated Learning for Multi-Institutional CT Imagingcited by 14
  23. 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient Splittingcited by 14
  24. 2023A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Datacited by 14
  25. 2024Synergizing Foundation Models and Federated Learning: A Surveycited by 14
  26. 2021Secure Distributed Training at Scalecited by 12
  27. 2022Federated Learning Attacks and Defenses: A Surveycited by 12
  28. 2023BAFFLE: A Baseline of Backpropagation-Free Federated Learningcited by 12
  29. 2023Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learningcited by 12
  30. 2023Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Ratescited by 12
  31. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12
  32. 2023Source Inference Attacks: Beyond Membership Inference Attacks in Federated Learningcited by 11
  33. 2021FedMood: Federated Learning on Mobile Health Data for Mood Detectioncited by 10
  34. 2022Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutationcited by 10
  35. 2023Federated Learning Across Decentralized and Unshared Archives for Remote Sensing Image Classificationcited by 10
  36. 2025Safety of Embodied Navigation: A Surveycited by 10
  37. 2021Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategiescited by 9
  38. 2023Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneitycited by 9

50 most cited of 166 All 166 (JSON)