mlsanityData to 14 Oct 2026

Eluding Secure Aggregation in Federated Learning via Model Inconsistency

arXiv 2111.07380 ↗First posted 14 Nov 2021cs.LG cs.CRcited by 67

Not on the map. Why?

Abstract (arXiv)

Secure aggregation is a cryptographic protocol that securely computes the aggregation of its inputs. It is pivotal in keeping model updates private in federated learning. Indeed, the use of secure aggregation prevents the server from learning the value and the source of the individual model updates provided by the users, hampering inference and data attribution attacks. In this work, we show that a malicious server can easily elude secure aggregation as if the latter were not in place. We devise two different attacks capable of inferring information on individual private training datasets, independently of the number of users participating in the secure aggregation. This makes them concrete threats in large-scale, real-world federated learning applications. The attacks are generic and equally effective regardless of the secure aggregation protocol used. They exploit a vulnerability of the federated learning protocol caused by incorrect usage of secure aggregation and lack of parameter validation. Our work demonstrates that current implementations of federated learning with secure aggregation offer only a "false sense of security".

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Builds on 44 of its 77 references that are in the map. First posted on arXiv 14 Nov 2021.

Builds on

44 of 77 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  6. 2016Densely Connected Convolutional Networkscited by 6,720
  7. 2016Layer Normalizationcited by 5,669
  8. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  9. 2016Deep Learning with Differential Privacycited by 2,728
  10. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  11. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  12. 2019Deep Leakage from Gradientscited by 1,021
32 more
  1. 2019Towards Federated Learning at Scale: System Designcited by 832
  2. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  3. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  4. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  5. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  6. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  7. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  8. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  9. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  10. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  11. 2019Robust Aggregation for Federated Learningcited by 317
  12. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
  13. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 204
  14. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  15. 2020Salvaging Federated Learning by Local Adaptationcited by 142
  16. 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 130
  17. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
  18. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 108
  19. 2020R-GAP: Recursive Gradient Attack on Privacycited by 97
  20. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  21. 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
  22. 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
  23. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 78
  24. 2020Training Production Language Models without Memorizing User Datacited by 68
  25. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 68
  26. 2020FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learningcited by 61
  27. 2019HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learningcited by 51
  28. 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43
  29. 2020Communication-Computation Efficient Secure Aggregation for Federated Learningcited by 18
  30. 2021Byzantine-Robust and Privacy-Preserving Framework for FedMLcited by 14
  31. 2021Secure Aggregation for Buffered Asynchronous Federated Learningcited by 10
  32. 2020Scalable Privacy-Preserving Distributed Learningcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 19; 2024: 14; 2025: 12; 2026: 11.

67 papers.

Sort:

By area:

  1. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
  2. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 73
  3. 2024Byzantine-Robust Decentralized Federated Learningcited by 48
  4. 2022Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queriescited by 40
  5. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 36
  6. 2022On the Impossible Safety of Large AI Modelscited by 28
  7. 2022On the (In)security of Peer-to-Peer Decentralized Machine Learningcited by 23
  8. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  9. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 21
  10. 2023Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learningcited by 17
  11. 2023Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregationcited by 16
  12. 2023A Survey for Federated Learning Evaluations: Goals and Measurescited by 16
38 more
  1. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  2. 2022Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graphcited by 11
  3. 2023Client-specific Property Inference against Secure Aggregation in Federated Learningcited by 9
  4. 2023The Resource Problem of Using Linear Layer Leakage Attack in Federated Learningcited by 9
  5. 2023Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learningcited by 9
  6. 2025Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attackscited by 9
  7. 2022ScionFL: Efficient and Robust Secure Quantized Aggregationcited by 8
  8. 2023Can Decentralized Learning be more robust than Federated Learning?cited by 6
  9. 2023Samplable Anonymous Aggregation for Private Federated Data Analysiscited by 6
  10. 2024Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learningcited by 6
  11. 2022Hierarchical Federated Learning with Privacycited by 4
  12. 2022Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Predictioncited by 4
  13. 2023Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learningcited by 4
  14. 2024Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimationcited by 4
  15. 2025Vertical Federated Learning in Practice: The Good, the Bad, and the Uglycited by 4
  16. 2022Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learningcited by 3
  17. 2023SRATTA : Sample Re-ATTribution Attack of Secure Aggregation in Federated Learningcited by 3
  18. 2023Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applicationscited by 3
  19. 2024MedLeak: Multimodal Medical Data Leakage in Secure Federated Learning with Crafted Modelscited by 3
  20. 2025Gradient Inversion Attacks on Parameter-Efficient Fine-Tuningcited by 3
  21. 2022Refiner: Data Refining against Gradient Leakage Attacks in Federated Learningcited by 2
  22. 2023WW-FL: Secure and Private Large-Scale Federated Learningcited by 2
  23. 2023Privacy Preserving Federated Learning with Convolutional Variational Bottleneckscited by 2
  24. 2024Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learningcited by 2
  25. 2024Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomycited by 2
  26. 2024The Power of Bias: Optimizing Client Selection in Federated Learning with Heterogeneous Differential Privacycited by 2
  27. 2025Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learningcited by 2
  28. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  29. 2023AnoFel: Supporting Anonymity for Privacy-Preserving Federated Learningcited by 1
  30. 2023RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulationcited by 1
  31. 2025Zero-Knowledge Federated Learning: A New Trustworthy and Privacy-Preserving Distributed Learning Paradigmcited by 1
  32. 2025EC-LDA : Label Distribution Inference Attack against Federated Graph Learning with Embedding Compressioncited by 1
  33. 2025Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learningcited by 1
  34. 2026From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuningcited by 1
  35. 2026Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Datacited by 1
  36. 2023OASIS: Offsetting Active Reconstruction Attacks in Federated Learningcited by 0
  37. 2024Fluent: Round-efficient Secure Aggregation for Private Federated Learningcited by 0
  38. 2024Differentially Private Federated Learning without Noise Addition: When is it Possible?cited by 0

50 most cited of 67 All 67 (JSON)