mlsanityData to 14 Oct 2026

On Model Protection in Federated Learning against Eavesdropping Attacks

arXiv 2504.02114 ↗First posted 2 Apr 2025cs.CR cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

In this study, we investigate the protection offered by federated learning algorithms against eavesdropping adversaries. In our model, the adversary is capable of intercepting model updates transmitted from clients to the server, enabling it to create its own estimate of the model. Unlike previous research, which predominantly focuses on safeguarding client data, our work shifts attention protecting the client model itself. Through a theoretical analysis, we examine how various factors, such as the probability of client selection, the structure of local objective functions, global aggregation at the server, and the eavesdropper's capabilities, impact the overall level of protection. We further validate our findings through numerical experiments, assessing the protection by evaluating the model accuracy achieved by the adversary. Finally, we compare our results with methods based on differential privacy, underscoring their limitations in this specific context.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

29 of 47 references.

References · 29

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2019Deep Leakage from Gradientscited by 1,021
  5. 2019Towards Federated Learning at Scale: System Designcited by 832
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  7. 2017Federated Multi-Task Learningcited by 672
  8. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  9. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  10. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  11. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  12. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
17 more
  1. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  2. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  3. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  4. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  5. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  6. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  7. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 130
  8. 2020FedDANE: A Federated Newton-Type Methodcited by 76
  9. 2024Byzantine-Robust Decentralized Federated Learningcited by 48
  10. 2021Gradient Leakage Attack Resilient Deep Learningcited by 18
  11. 2020A Survey of Published Attacks on Intel SGXcited by 10
  12. 2019Privacy-Preserving Average Consensus via State Decompositioncited by 8
  13. 2021Multi-Agent Consensus Subject to Communication and Privacy Constraintscited by 2
  14. 2017State-Secrecy Codes for Networked Linear Systemscited by 1
  15. 2020Distortion based Light-weight Security for Cyber-Physical Systemscited by 1
  16. 2024Ensuring System-Level Protection against Eavesdropping Adversaries in Distributed Dynamical Systemscited by 1
  17. 2024Federated Learning Nodes Can Reconstruct Peers' Image Datacited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025ModShift: Model Privacy via Designed Shiftscited by 1
  2. 2026MaxModShift: Model Privacy via Designed Shiftscited by 0