mlsanityData to 14 Oct 2026

On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directions

arXiv 2508.13730 ↗First posted 19 Aug 2025cs.CR cs.AI cs.DCcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is an emerging distributed machine learning paradigm enabling multiple clients to train a global model collaboratively without sharing their raw data. While FL enhances data privacy by design, it remains vulnerable to various security and privacy threats. This survey provides a comprehensive overview of more than 200 papers regarding the state-of-the-art attacks and defense mechanisms developed to address these challenges, categorizing them into security-enhancing and privacy-preserving techniques. Security-enhancing methods aim to improve FL robustness against malicious behaviors such as byzantine attacks, poisoning, and Sybil attacks. At the same time, privacy-preserving techniques focus on protecting sensitive data through cryptographic approaches, differential privacy, and secure aggregation. We critically analyze the strengths and limitations of existing methods, highlight the trade-offs between privacy, security, and model performance, and discuss the implications of non-IID data distributions on the effectiveness of these defenses. Furthermore, we identify open research challenges and future directions, including the need for scalable, adaptive, and energy-efficient solutions operating in dynamic and heterogeneous FL environments. Our survey aims to guide researchers and practitioners in developing robust and privacy-preserving FL systems, fostering advancements safeguarding collaborative learning frameworks' integrity and confidentiality.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 91 of its 205 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

91 of 205 references.

References · 91

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
  4. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  5. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  6. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  7. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  8. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  9. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
  10. 2019Robust Aggregation for Federated Learningcited by 317
  11. 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
  12. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 300
38 more
  1. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  2. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  3. 2020Differentially Private Learning Needs Better Features (or Much More Data)cited by 235
  4. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 197
  5. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  6. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  7. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
  8. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 136
  9. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  10. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
  11. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 118
  12. 2024On Protecting the Data Privacy of Large Language Models (LLMs): A Surveycited by 96
  13. 2018Generalized Byzantine-tolerant SGDcited by 95
  14. 2020Provable Defense against Privacy Leakage in Federated Learning from Representation Perspectivecited by 94
  15. 2020Fairness-aware Agnostic Federated Learningcited by 87
  16. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  17. 2022NVIDIA FLARE: Federated Learning from Simulation to Real-Worldcited by 80
  18. 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 77
  19. 2019Detailed comparison of communication efficiency of split learning and federated learningcited by 77
  20. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  21. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  22. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
  23. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
  24. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directionscited by 63
  25. 2021OpenFL: An open-source framework for Federated Learningcited by 58
  26. 2020Free-rider Attacks on Model Aggregation in Federated Learningcited by 57
  27. 2019Zeno++: Robust Fully Asynchronous SGDcited by 53
  28. 2019Free-riders in Federated Learning: Attacks and Defensescited by 49
  29. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  30. 2022Do Gradient Inversion Attacks Make Federated Learning Unsafe?cited by 44
  31. 2020Mitigating Backdoor Attacks in Federated Learningcited by 39
  32. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 39
  33. 2023FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning Systemcited by 38
  34. 2017Prio: Private, Robust, and Scalable Computation of Aggregate Statisticscited by 36
  35. 2021FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspectivecited by 36
  36. 2020Advancements of federated learning towards privacy preservation: from federated learning to split learningcited by 34
  37. 2020Federated Transfer Learning: concept and applicationscited by 32
  38. 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32

50 most cited of 91 All 91 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifierscited by 0
  2. 2026Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AIcited by 0