mlsanityData to 7 Oct 2026

Gradient Inversion with Generative Image Prior

arXiv 2110.14962 ↗First posted 28 Oct 2021cs.LGcited by 101

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a distributed learning framework, in which the local data never leaves clients devices to preserve privacy, and the server trains models on the data via accessing only the gradients of those local data. Without further privacy mechanisms such as differential privacy, this leaves the system vulnerable against an attacker who inverts those gradients to reveal clients sensitive data. However, a gradient is often insufficient to reconstruct the user data without any prior knowledge. By exploiting a generative model pretrained on the data distribution, we demonstrate that data privacy can be easily breached. Further, when such prior knowledge is unavailable, we investigate the possibility of learning the prior from a sequence of gradients seen in the process of FL training. We experimentally show that the prior in a form of generative model is learnable from iterative interactions in FL. Our findings strongly suggest that additional mechanisms are necessary to prevent privacy leakage in FL.

Key facts. Cited by 101 papers in the map (data through 7 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 28 Oct 2021.

Builds on

28 of 35 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  11. 2017Deep Image Priorcited by 1,097
  12. 2019Deep Leakage from Gradientscited by 1,004
16 more
  1. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  2. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  3. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
  4. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  5. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 471
  6. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  7. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  8. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  9. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  10. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  11. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  12. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  13. 2019Seeing What a GAN Cannot Generatecited by 148
  14. 2020R-GAP: Recursive Gradient Attack on Privacycited by 95
  15. 2020Siloed Federated Learning for Multi-Centric Histopathology Datasetscited by 61
  16. 2020Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attackscited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 21; 2023: 20; 2024: 32; 2025: 18; 2026: 8.

101 papers.

Sort:

By area:

  1. 2023Dataset Distillation: A Comprehensive Reviewcited by 126
  2. 2022Recovering Private Text in Federated Learning of Language Modelscited by 67
  3. 2022LAMP: Extracting Text from Gradients with Language Model Priorscited by 52
  4. 2022GradViT: Gradient Inversion of Vision Transformerscited by 52
  5. 2023GIFD: A Generative Gradient Inversion Method with Feature Domain Optimizationcited by 45
  6. 2023Bounding Training Data Reconstruction in DP-SGDcited by 42
  7. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 37
  8. 2021Bayesian Framework for Gradient Leakagecited by 34
  9. 2022Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learningcited by 30
  10. 2022Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysiscited by 29
  11. 2022Reconstructing Training Data from Model Gradient, Provablycited by 27
  12. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
38 more
  1. 2022FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentationcited by 24
  2. 2022CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learningcited by 24
  3. 2021APRIL: Finding the Achilles' Heel on Privacy for Vision Transformerscited by 23
  4. 2022On the (In)security of Peer-to-Peer Decentralized Machine Learningcited by 23
  5. 2022DYNAFED: Tackling Client Data Heterogeneity with Global Dynamicscited by 22
  6. 2022Few-Shot Unlearning by Model Inversioncited by 17
  7. 2022Genie: Show Me the Data for Quantizationcited by 17
  8. 2023Unlocking Accuracy and Fairness in Differentially Private Image Classificationcited by 16
  9. 2022AGIC: Approximate Gradient Inversion Attack on Federated Learningcited by 15
  10. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  11. 2022TabLeak: Tabular Data Leakage in Federated Learningcited by 13
  12. 2024Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attackscited by 13
  13. 2024GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Searchcited by 13
  14. 2022Dropout is NOT All You Need to Prevent Gradient Leakagecited by 11
  15. 2022Concealing Sensitive Samples against Gradient Leakage in Federated Learningcited by 11
  16. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
  17. 2023Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learningcited by 10
  18. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspectivecited by 9
  19. 2025Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attackscited by 9
  20. 2024Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attackscited by 7
  21. 2022Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Designcited by 6
  22. 2023Understanding Deep Gradient Leakage via Inversion Influence Functionscited by 6
  23. 2023Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learningcited by 6
  24. 2024Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-offcited by 6
  25. 2024Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimizationcited by 6
  26. 2023Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusioncited by 5
  27. 2024Data Reconstruction Attacks and Defenses: A Systematic Evaluationcited by 5
  28. 2024Recovering Labels from Local Updates in Federated Learningcited by 5
  29. 2024Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstructioncited by 5
  30. 2025CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Samplingcited by 5
  31. 2023Gradient Leakage Defense with Key-Lock Module for Federated Learningcited by 4
  32. 2023Temporal Gradient Inversion Attacks with Robust Optimizationcited by 4
  33. 2023Privacy Risks in Reinforcement Learning for Household Robotscited by 4
  34. 2023Approximate and Weighted Data Reconstruction Attack in Federated Learningcited by 4
  35. 2023Client-side Gradient Inversion Against Federated Learning from Poisoningcited by 4
  36. 2023Generator Born from Classifiercited by 4
  37. 2024Towards Eliminating Hard Label Constraints in Gradient Inversion Attackscited by 4
  38. 2024DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Imagescited by 4

50 most cited of 101 All 101 (JSON)