mlsanityData to 14 Oct 2026

Towards General Deep Leakage in Federated Learning

arXiv 2110.09074 ↗First posted 18 Oct 2021cs.LG cs.AIcited by 40

Not on the map. Why?

Abstract (arXiv)

Unlike traditional central training, federated learning (FL) improves the performance of the global model by sharing and aggregating local models rather than local data to protect the users' privacy. Although this training approach appears secure, some research has demonstrated that an attacker can still recover private data based on the shared gradient information. This on-the-fly reconstruction attack deserves to be studied in depth because it can occur at any stage of training, whether at the beginning or at the end of model training; no relevant dataset is required and no additional models need to be trained. We break through some unrealistic assumptions and limitations to apply this reconstruction attack in a broader range of scenarios. We propose methods that can reconstruct the training data from shared gradients or weights, corresponding to the FedSGD and FedAvg usage scenarios, respectively. We propose a zero-shot approach to restore labels even if there are duplicate labels in the batch. We study the relationship between the label and image restoration. We find that image restoration fails even if there is only one incorrectly inferred label in the batch; we also find that when batch images have the same label, the corresponding image is restored as a fusion of that class of images. Our approaches are evaluated on classic image benchmarks, including CIFAR-10 and ImageNet. The batch size, image quality, and the adaptability of the label distribution of our approach exceed those of GradInversion, the state-of-the-art.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 11 of its 14 references that are in the map. First posted on arXiv 18 Oct 2021.

Builds on

11 of 14 references.

References · 11

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2019Deep Leakage from Gradientscited by 1,021
  4. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  5. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  6. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  7. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  8. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  9. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  10. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  11. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 122

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 10; 2024: 9; 2025: 8; 2026: 4.

40 papers.

Sort:

By area:

  1. 2022LAMP: Extracting Text from Gradients with Language Model Priorscited by 54
  2. 2023FedMultimodal: A Benchmark For Multimodal Federated Learningcited by 51
  3. 2021Bayesian Framework for Gradient Leakagecited by 34
  4. 2023A Survey on Dataset Distillation: Approaches, Applications and Future Directionscited by 32
  5. 2022Data Leakage in Federated Averagingcited by 26
  6. 2022AGIC: Approximate Gradient Inversion Attack on Federated Learningcited by 15
  7. 2024SPEAR:Exact Gradient Inversion of Batches in Federated Learningcited by 15
  8. 2024DAGER: Exact Gradient Inversion for Large Language Modelscited by 14
  9. 2022TabLeak: Tabular Data Leakage in Federated Learningcited by 13
  10. 2021Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settingscited by 12
  11. 2023Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learningcited by 11
  12. 2023The Resource Problem of Using Linear Layer Leakage Attack in Federated Learningcited by 9
28 more
  1. 2023A Comprehensive Study on Dataset Distillation: Performance, Privacy, Robustness and Fairnesscited by 9
  2. 2023Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learningcited by 9
  3. 2025Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attackscited by 9
  4. 2022A Secure Federated Learning Framework for Residential Short Term Load Forecastingcited by 7
  5. 2022The Risks of Machine Learning Systemscited by 5
  6. 2024Recovering Labels from Local Updates in Federated Learningcited by 5
  7. 2025GRAIN: Exact Graph Reconstruction from Gradientscited by 5
  8. 2023Probably Approximately Correct Federated Learningcited by 4
  9. 2023Temporal Gradient Inversion Attacks with Robust Optimizationcited by 4
  10. 2023PPIDSG: A Privacy-Preserving Image Distribution Sharing Scheme with GAN in Federated Learningcited by 4
  11. 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attackscited by 4
  12. 2024No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learningcited by 3
  13. 2024Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learningcited by 2
  14. 2024FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defensescited by 1
  15. 2025EC-LDA : Label Distribution Inference Attack against Federated Graph Learning with Embedding Compressioncited by 1
  16. 2025AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networkscited by 1
  17. 2026No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learningcited by 1
  18. 2022Deep leakage from gradientscited by 0
  19. 2023AI Models Close to your Chest: Robust Federated Learning Strategies for Multi-site CTcited by 0
  20. 2024Privacy Attack in Federated Learning is Not Easy: An Experimental Studycited by 0
  21. 2024GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learningcited by 0
  22. 2025TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting Modelscited by 0
  23. 2025Secure Generalization through Stochastic Bidirectional Parameter Updates Using Dual-Gradient Mechanismcited by 0
  24. 2025DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systemscited by 0
  25. 2025Evaluating Selective Encryption Against Gradient Inversion Attackscited by 0
  26. 2026SpooFL: Spoofing Federated Learningcited by 0
  27. 2026SOMP: Scalable Gradient Inversion for Large Language Models via Subspace-Guided Orthogonal Matching Pursuitcited by 0
  28. 2026TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimizationcited by 0