mlsanityData to 14 Oct 2026

On the (In)security of Peer-to-Peer Decentralized Machine Learning

arXiv 2205.08443 ↗First posted 17 May 2022cs.CR cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning -- a collaborative machine learning framework aimed at addressing the main limitations of federated learning. We introduce a suite of novel attacks for both passive and active decentralized adversaries. We demonstrate that, contrary to what is claimed by decentralized learning proposers, decentralized learning does not offer any security advantage over federated learning. Rather, it increases the attack surface enabling any user in the system to perform privacy attacks such as gradient inversion, and even gain full control over honest users' local model. We also show that, given the state of the art in protections, privacy-preserving configurations of decentralized learning require fully connected networks, losing any practical advantage over the federated setup and therefore completely defeating the objective of the decentralized approach.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 51 of its 80 references that are in the map. First posted on arXiv 17 May 2022.

Builds on

51 of 80 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  6. 2019Deep Leakage from Gradientscited by 1,021
  7. 2021Membership Inference Attacks From First Principlescited by 878
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  9. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  10. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  11. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  12. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
38 more
  1. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 367
  2. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  3. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  4. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  5. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 248
  6. 2019Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communicationcited by 221
  7. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 204
  8. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  9. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  10. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  11. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  12. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
  13. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
  14. 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 117
  15. 2021Decentralized Federated Averagingcited by 114
  16. 2019Decentralized Deep Learning with Arbitrary Communication Compressioncited by 111
  17. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 108
  18. 2021Gradient Inversion with Generative Image Priorcited by 101
  19. 2022Truth Serum: Poisoning Machine Learning Models to Reveal Their Secretscited by 101
  20. 2020R-GAP: Recursive Gradient Attack on Privacycited by 97
  21. 2018Understanding Membership Inferences on Well-Generalized Learning Modelscited by 90
  22. 2019Peer-to-peer Federated Learning on Graphscited by 85
  23. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 78
  24. 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 77
  25. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 73
  26. 2019MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Samplingcited by 67
  27. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
  28. 2019Decentralized Federated Learning: A Segmented Gossip Approachcited by 64
  29. 2021Exponential Graph is Provably Efficient for Decentralized Deep Trainingcited by 56
  30. 2017Personalized and Private Peer-to-Peer Machine Learningcited by 54
  31. 2021RelaySum for Decentralized Deep Learning on Heterogeneous Datacited by 39
  32. 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
  33. 2019Central Server Free Federated Learning over Single-sided Trust Social Networkscited by 33
  34. 2020Decentralized Federated Learning via SGD over Wireless D2D Networkscited by 33
  35. 2021On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Modelscited by 31
  36. 2020Privacy Amplification by Decentralizationcited by 28
  37. 2021IPLS : A Framework for Decentralized Federated Learningcited by 26
  38. 2021BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learningcited by 16

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 10; 2025: 7; 2026: 5.

23 papers.

Sort:

  1. 2024Differentially Private Decentralized Learning with Random Walkscited by 8
  2. 2024Privacy Attacks in Decentralized Learningcited by 8
  3. 2024Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimizationcited by 6
  4. 2024Boosting Asynchronous Decentralized Learning with Model Fragmentationcited by 6
  5. 2024Privacy-Preserving Aggregation for Decentralized Learning with Byzantine-Robustnesscited by 4
  6. 2025From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challengescited by 4
  7. 2025Byzantine-Resilient Federated Learning via Distributed Optimizationcited by 3
  8. 2025Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via f-Differential Privacycited by 3
  9. 2024Communication-Efficient Secure Aggregation in Decentralized Learningcited by 2
  10. 2025Differential Privacy Analysis of Decentralized Gossip Averaging under Varying Threat Modelscited by 2
  11. 2025On the Security and Privacy of Federated Learning: A Survey with Attacks, Defenses, Frameworks, Applications, and Future Directionscited by 2
  12. 2025Unified Privacy Guarantees for Decentralized Learning via Matrix Factorizationcited by 2
11 more
  1. 2023Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensuscited by 1
  2. 2024On the Conflict of Robustness and Learning in Collaborative Machine Learningcited by 1
  3. 2024Fair Decentralized Learningcited by 1
  4. 2024Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learningcited by 0
  5. 2024Fed-Credit: Robust Federated Learning with Credibility Managementcited by 0
  6. 2025Dropout-Robust Mechanisms for Differentially Private and Fully Decentralized Mean Estimationcited by 0
  7. 2026TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learningcited by 0
  8. 2026BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learningcited by 0
  9. 2026Optimizing Byzantine Node Placement in Decentralized Federated Learningcited by 0
  10. 2026Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaborationcited by 0
  11. 2026When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learningcited by 0