mlsanityData to 14 Oct 2026

Federated Learning Nodes Can Reconstruct Peers' Image Data

arXiv 2410.04661 ↗First posted 7 Oct 2024cs.LG cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a privacy-preserving machine learning framework that enables multiple nodes to train models on their local data and periodically average weight updates to benefit from other nodes' training. Each node's goal is to collaborate with other nodes to improve the model's performance while keeping its training data private. However, this framework does not guarantee data privacy. Prior work has shown that the gradient-sharing steps in FL can be vulnerable to data reconstruction attacks from an honest-but-curious central server. In this work, we show that an honest-but-curious node/client can also launch attacks to reconstruct peers' image data through gradient inversion, presenting a severe privacy risk. We demonstrate that a single client can silently reconstruct other clients' private images using diluted information available within consecutive updates. We leverage state-of-the-art diffusion models to enhance the perceptual quality and recognizability of the reconstructed images, further demonstrating the risk of information leakage at a semantic level. This highlights the need for more robust privacy-preserving mechanisms that protect against silent client-side attacks during federated training.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 7 Oct 2024.

Builds on

23 of 33 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  6. 2019Advances and Open Problems in Federated Learningcited by 3,046
  7. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  8. 2019Deep Leakage from Gradientscited by 1,021
  9. 2022Denoising Diffusion Restoration Modelscited by 963
  10. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  11. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  12. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
11 more
  1. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizercited by 262
  2. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 118
  3. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 108
  4. 2020Provable Defense against Privacy Leakage in Federated Learning from Representation Perspectivecited by 94
  5. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 73
  6. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 47
  7. 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43
  8. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 39
  9. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 36
  10. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 21
  11. 2020Is Network the Bottleneck of Distributed Training?cited by 20

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025On Model Protection in Federated Learning against Eavesdropping Attackscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models
  2. 2024Gradient Inversion of Federated Diffusion Models
  3. 2025Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
  4. 2025DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences
  5. 2024Privacy in Federated Learning
  6. 2025Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy
  7. 2025Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
  8. 2023Federated Learning with Diffusion Models for Privacy-Sensitive Vision Tasks