mlsanityData to 7 Oct 2026

The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape

arXiv 2405.03636 ↗First posted 6 May 2024cs.CR cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices, and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important privacy-preserving technology that enables collaborative training of machine learning models without the need to send the raw, potentially sensitive, data to a central server. However, the fundamental premise that sending model updates to a server is privacy-preserving only holds if the updates cannot be "reverse engineered" to infer information about the private training data. It has been shown under a wide variety of settings that this privacy premise does not hold. In this survey paper, we provide a comprehensive literature review of the different privacy attacks and defense methods in FL. We identify the current limitations of these attacks and highlight the settings in which the privacy of an FL client can be broken. We further dissect some of the successful industry applications of FL and draw lessons for future successful adoption. We survey the emerging landscape of privacy regulation for FL and conclude with future directions for taking FL toward the cherished goal of generating accurate models while preserving the privacy of the data from its participants.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 81 of its 146 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

81 of 146 references.

References · 81

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  6. 2021Membership Inference Attacks From First Principlescited by 839
  7. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  8. 2017Renyi Differential Privacycited by 643
  9. 2020The Future of Digital Health with Federated Learningcited by 625
  10. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  11. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  12. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
38 more
  1. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  2. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  3. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  4. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 361
  5. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  6. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  7. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  8. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  9. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  10. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  11. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
  12. 2022Unlocking High-Accuracy Differentially Private Image Classification through Scalecited by 218
  13. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
  14. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 174
  15. 2020A Survey of Privacy Attacks in Machine Learningcited by 143
  16. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  17. 2023Privacy Auditing with One (1) Training Runcited by 119
  18. 2018Stealing Hyperparameters in Machine Learningcited by 115
  19. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 108
  20. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 106
  21. 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
  22. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 89
  23. 2022Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learningcited by 81
  24. 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
  25. 2022NVIDIA FLARE: Federated Learning from Simulation to Real-Worldcited by 78
  26. 2022I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defencescited by 75
  27. 2021Practical Blind Membership Inference Attack via Differential Comparisonscited by 73
  28. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 72
  29. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 72
  30. 2018Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacycited by 66
  31. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  32. 2023Federated Learning of Gboard Language Models with Differential Privacycited by 64
  33. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
  34. 2020Federated Learning for Breast Density Classification: A Real-World Implementationcited by 62
  35. 2020FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learningcited by 60
  36. 2022GradViT: Gradient Inversion of Vision Transformerscited by 52
  37. 2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 51
  38. 2021The Federated Tumor Segmentation (FeTS) Challengecited by 49

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

By area:

  1. 2025Energy-Latency Attacks: A New Adversarial Threat to Deep Learningcited by 5
  2. 2025When Federated Learning Meets Quantum Computing: Survey and Research Opportunitiescited by 5
  3. 2025The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learningcited by 2
  4. 2026Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learningcited by 2
  5. 2025Securing Genomic Data Against Inference Attacks in Federated Learning Environmentscited by 1
  6. 2025FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolutioncited by 0
  7. 2025FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learningcited by 0
  8. 2025FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalizationcited by 0
  9. 2026Trust-Based Incentive Mechanisms in Semi-Decentralized Federated Learning Systemscited by 0
  10. 2026Rashomon Sets and Model Multiplicity in Federated Learningcited by 0
  11. 2026AI Security Research Should Better Incentivize Defense Researchcited by 0
  12. 2026Color Matters: Trigger Color Affects Success in Federated Backdoor Attackscited by 0
1 more
  1. 2026Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offscited by 0