mlsanityData to 7 Oct 2026

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

arXiv 2306.03013 ↗First posted 5 Jun 2023cs.CR cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. However, many concerns regarding the client-side detectability of MS attacks were raised, questioning their practicality. In this work, for the first time, we thoroughly study client-side detectability. We first demonstrate that all prior MS attacks are detectable by principled checks, and formulate a necessary set of requirements that a practical MS attack must satisfy. Next, we propose SEER, a novel attack framework that satisfies these requirements. The key insight of SEER is the use of a secret decoder, jointly trained with the shared model. We show that SEER can steal user data from gradients of realistic networks, even for large batch sizes of up to 512 and under secure aggregation. Our work is a promising step towards assessing the true vulnerability of federated learning in real-world settings.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

35 of 45 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2019Deep Leakage from Gradientscited by 1,004
  7. 2018Robustness May Be at Odds with Accuracycited by 873
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  9. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  10. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  11. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  12. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
23 more
  1. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
  2. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  3. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  4. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  5. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  6. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 106
  7. 2020R-GAP: Recursive Gradient Attack on Privacycited by 95
  8. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 84
  9. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  10. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 72
  11. 2022Recovering Private Text in Federated Learning of Language Modelscited by 67
  12. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  13. 2022Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Modelscited by 52
  14. 2022LAMP: Extracting Text from Gradients with Language Model Priorscited by 52
  15. 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43
  16. 2021Towards General Deep Leakage in Federated Learningcited by 40
  17. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 37
  18. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 35
  19. 2021Bayesian Framework for Gradient Leakagecited by 34
  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. 2023Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregationcited by 16
  23. 2022Federated Learning for Tabular Data: Exploring Potential Risk to Privacycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 1.

9 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
  3. 2025Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learningcited by 2
  4. 2025DBA-DFL: Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learningcited by 1
  5. 2026No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learningcited by 1
  6. 2024QBI: Quantile-Based Bias Initialization for Efficient Private Data Reconstruction in Federated Learningcited by 0
  7. 2025DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systemscited by 0
  8. 2025Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updatescited by 0
  9. 2025On the Detectability of Active Gradient Inversion Attacks in Federated Learningcited by 0