mlsanityData to 14 Oct 2026

Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks

arXiv 2503.11514 ↗First posted 13 Mar 2025cs.CR cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) has emerged as a promising privacy-preserving collaborative model training paradigm without sharing raw data. However, recent studies have revealed that private information can still be leaked through shared gradient information and attacked by Gradient Inversion Attacks (GIA). While many GIA methods have been proposed, a detailed analysis, evaluation, and summary of these methods are still lacking. Although various survey papers summarize existing privacy attacks in FL, few studies have conducted extensive experiments to unveil the effectiveness of GIA and their associated limiting factors in this context. To fill this gap, we first undertake a systematic review of GIA and categorize existing methods into three types, i.e., textitoptimization-based GIA (OP-GIA), textitgeneration-based GIA (GEN-GIA), and textitanalytics-based GIA (ANA-GIA). Then, we comprehensively analyze and evaluate the three types of GIA in FL, providing insights into the factors that influence their performance, practicality, and potential threats. Our findings indicate that OP-GIA is the most practical attack setting despite its unsatisfactory performance, while GEN-GIA has many dependencies and ANA-GIA is easily detectable, making them both impractical. Finally, we offer a three-stage defense pipeline to users when designing FL frameworks and protocols for better privacy protection and share some future research directions from the perspectives of attackers and defenders that we believe should be pursued. We hope that our study can help researchers design more robust FL frameworks to defend against these attacks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 70 of its 117 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

70 of 117 references.

References · 70

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  7. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  8. 2014Going Deeper with Convolutionscited by 4,241
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  11. 2019Deep Leakage from Gradientscited by 1,021
  12. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
38 more
  1. 2014Convex Optimization: Algorithms and Complexitycited by 575
  2. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  3. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  4. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  5. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  6. 2018Distributed learning of deep neural network over multiple agentscited by 279
  7. 2015Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decompositioncited by 243
  8. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  9. 2024Improving LoRA in Privacy-preserving Federated Learningcited by 161
  10. 2021Federated Learning for Open Bankingcited by 141
  11. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
  12. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 108
  13. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  14. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  15. 2021Gradient Inversion with Generative Image Priorcited by 101
  16. 2020R-GAP: Recursive Gradient Attack on Privacycited by 97
  17. 2024Selective Aggregation for Low-Rank Adaptation in Federated Learningcited by 80
  18. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 73
  19. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  20. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
  21. 2020A Framework for Evaluating Gradient Leakage Attacks in Federated Learningcited by 64
  22. 2024Dual-Personalizing Adapter for Federated Foundation Modelscited by 55
  23. 2022GradViT: Gradient Inversion of Vision Transformerscited by 53
  24. 2023GIFD: A Generative Gradient Inversion Method with Feature Domain Optimizationcited by 45
  25. 2022Do Gradient Inversion Attacks Make Federated Learning Unsafe?cited by 44
  26. 2021Gradient-Leakage Resilient Federated Learningcited by 40
  27. 2021Towards General Deep Leakage in Federated Learningcited by 40
  28. 2022A Survey on Gradient Inversion: Attacks, Defenses and Future Directionscited by 40
  29. 2022Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imagingcited by 39
  30. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 39
  31. 2021GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learningcited by 36
  32. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 36
  33. 2022Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learningcited by 30
  34. 2022Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysiscited by 29
  35. 2021PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakagecited by 28
  36. 2020SAPAG: A Self-Adaptive Privacy Attack From Gradientscited by 27
  37. 2022Data Leakage in Federated Averagingcited by 26
  38. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 21

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language Modelscited by 6
  2. 2025Exploring Federated Pruning for Large Language Modelscited by 2
  3. 2025Practical Feasibility of Gradient Inversion Attacks in Federated Learningcited by 2
  4. 2025SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learningcited by 1
  5. 2025SelectiveShield: Lightweight Hybrid Defense Against Gradient Leakage in Federated Learningcited by 0
  6. 2026Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Modelscited by 0
  7. 2026Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Modelscited by 0
  8. 2026When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learningcited by 0
  9. 2026SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMMcited by 0