mlsanityData to 7 Oct 2026

Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomy

arXiv 2405.10376 ↗First posted 16 May 2024cs.CR cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) has emerged as a leading paradigm for decentralized, privacy preserving machine learning training. However, recent research on gradient inversion attacks (GIAs) have shown that gradient updates in FL can leak information on private training samples. While existing surveys on GIAs have focused on the honest-but-curious server threat model, there is a dearth of research categorizing attacks under the realistic and far more privacy-infringing cases of malicious servers and clients. In this paper, we present a survey and novel taxonomy of GIAs that emphasize FL threat models, particularly that of malicious servers and clients. We first formally define GIAs and contrast conventional attacks with the malicious attacker. We then summarize existing honest-but-curious attack strategies, corresponding defenses, and evaluation metrics. Critically, we dive into attacks with malicious servers and clients to highlight how they break existing FL defenses, focusing specifically on reconstruction methods, target model architectures, target data, and evaluation metrics. Lastly, we discuss open problems and future research directions.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 48 references that are in the map. First posted on arXiv 16 May 2024.

Builds on

40 of 48 references.

References · 40

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Deep Leakage from Gradientscited by 1,004
  4. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  5. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  6. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  7. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  8. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  9. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  10. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 193
  11. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  12. 2020Federated Learning with Compression: Unified Analysis and Sharp Guaranteescited by 159
28 more
  1. 2020A Theory of Usable Information Under Computational Constraintscited by 153
  2. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  3. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 106
  4. 2021Gradient Inversion with Generative Image Priorcited by 101
  5. 2020R-GAP: Recursive Gradient Attack on Privacycited by 95
  6. 2020InstaHide: Instance-hiding Schemes for Private Distributed Learningcited by 90
  7. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  8. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 72
  9. 2022Recovering Private Text in Federated Learning of Language Modelscited by 67
  10. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  11. 2020A Framework for Evaluating Gradient Leakage Attacks in Federated Learningcited by 63
  12. 2022Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Modelscited by 52
  13. 2023GIFD: A Generative Gradient Inversion Method with Feature Domain Optimizationcited by 45
  14. 2022Do Gradient Inversion Attacks Make Federated Learning Unsafe?cited by 44
  15. 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43
  16. 2022A Survey on Gradient Inversion: Attacks, Defenses and Future Directionscited by 39
  17. 2023FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning Systemcited by 38
  18. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 37
  19. 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
  20. 2022Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learningcited by 30
  21. 2022Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysiscited by 29
  22. 2021APRIL: Finding the Achilles' Heel on Privacy for Vision Transformerscited by 23
  23. 2020Layer-wise Characterization of Latent Information Leakage in Federated Learningcited by 19
  24. 2020An Overview of Federated Deep Learning Privacy Attacks and Defensive Strategiescited by 18
  25. 2021Understanding Training-Data Leakage from Gradients in Neural Networks for Image Classificationcited by 16
  26. 2023Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregationcited by 16
  27. 2021Federated Learning Attacks Revisited: A Critical Discussion of Gaps, Assumptions, and Evaluation Setupscited by 5
  28. 2023Client-side Gradient Inversion Against Federated Learning from Poisoningcited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2025Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attackscited by 9
  2. 2024Geminio: Language-Guided Gradient Inversion Attacks in Federated Learningcited by 3