mlsanityData to 14 Oct 2026

CAFE: Catastrophic Data Leakage in Vertical Federated Learning

arXiv 2110.15122 ↗First posted 26 Oct 2021cs.LG cs.AIcited by 76

Not on the map. Why?

Abstract (arXiv)

Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate data recovery is often viewed as a promising defense strategy against data leakage. In this paper, we revisit this defense premise and propose an advanced data leakage attack with theoretical justification to efficiently recover batch data from the shared aggregated gradients. We name our proposed method as catastrophic data leakage in vertical federated learning (CAFE). Comparing to existing data leakage attacks, our extensive experimental results on vertical FL settings demonstrate the effectiveness of CAFE to perform large-batch data leakage attack with improved data recovery quality. We also propose a practical countermeasure to mitigate CAFE. Our results suggest that private data participated in standard FL, especially the vertical case, have a high risk of being leaked from the training gradients. Our analysis implies unprecedented and practical data leakage risks in those learning settings. The code of our work is available at https://github.com/DeRafael/CAFE.

Key facts. Cited by 76 papers in the map (data through 14 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

20 of 34 references.

References · 20

  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. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2019Deep Leakage from Gradientscited by 1,021
  5. 2018How To Backdoor Federated Learningcited by 765
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  7. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  8. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  9. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  10. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  11. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 300
  12. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
8 more
  1. 2020R-GAP: Recursive Gradient Attack on Privacycited by 97
  2. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 96
  3. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  4. 2020A Framework for Evaluating Gradient Leakage Attacks in Federated Learningcited by 64
  5. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 39
  6. 2020Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attackscited by 32
  7. 2020SAPAG: A Self-Adaptive Privacy Attack From Gradientscited by 27
  8. 2015FireCaffe: near-linear acceleration of deep neural network training on compute clusterscited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 28; 2024: 23; 2025: 13; 2026: 2.

76 papers.

Sort:

By area:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  2. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  3. 2022Vertical Federated Learning: Challenges, Methodologies and Experimentscited by 55
  4. 2022GradViT: Gradient Inversion of Vision Transformerscited by 53
  5. 2023Bounding Training Data Reconstruction in DP-SGDcited by 46
  6. 2023FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Modelscited by 17
  7. 2023Unlocking Accuracy and Fairness in Differentially Private Image Classificationcited by 16
  8. 2023Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challengescited by 14
  9. 2024Trustworthy Distributed AI Systems: Robustness, Privacy, and Governancecited by 14
  10. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  11. 2022TabLeak: Tabular Data Leakage in Federated Learningcited by 13
  12. 2023Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?cited by 13
38 more
  1. 2023Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learningcited by 11
  2. 2023FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscationcited by 10
  3. 2023BadVFL: Backdoor Attacks in Vertical Federated Learningcited by 10
  4. 2023Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learningcited by 9
  5. 2024Analysis of Privacy Leakage in Federated Large Language Modelscited by 9
  6. 2023Vertical Federated Learning: Taxonomies, Threats, and Prospectscited by 8
  7. 2023VFLAIR: A Research Library and Benchmark for Vertical Federated Learningcited by 8
  8. 2023Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Partiescited by 7
  9. 2024A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspectivecited by 7
  10. 2023Practical and General Backdoor Attacks against Vertical Federated Learningcited by 6
  11. 2023VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarkscited by 6
  12. 2023Understanding Deep Gradient Leakage via Inversion Influence Functionscited by 6
  13. 2024PraFFL: A Preference-Aware Scheme in Fair Federated Learningcited by 5
  14. 2022Enabling All In-Edge Deep Learning: A Literature Reviewcited by 4
  15. 2022Differentially Private Vertical Federated Learningcited by 4
  16. 2023Mutual Information Regularization for Vertical Federated Learningcited by 4
  17. 2023Secure Vertical Federated Learning Under Unreliable Connectivitycited by 4
  18. 2023Privacy-Preserving Remote Heart Rate Estimation from Facial Videoscited by 4
  19. 2023Temporal Gradient Inversion Attacks with Robust Optimizationcited by 4
  20. 2023PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Informationcited by 4
  21. 2023Privacy Risks in Reinforcement Learning for Household Robotscited by 4
  22. 2024VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purificationcited by 4
  23. 2024Gradient Inversion Attack on Graph Neural Networkscited by 4
  24. 2025Vertical Federated Learning in Practice: The Good, the Bad, and the Uglycited by 4
  25. 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Datacited by 3
  26. 2023Efficient Vertical Federated Learning with Secure Aggregationcited by 3
  27. 2023Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectivescited by 3
  28. 2024On the Efficiency of Privacy Attacks in Federated Learningcited by 3
  29. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  30. 2024A Self-Learning Multimodal Approach for Fake News Detectioncited by 3
  31. 2025From Risk to Resilience: Towards Assessing and Mitigating the Risk of Data Reconstruction Attacks in Federated Learningcited by 3
  32. 2022Data Stealing Attack on Medical Images: Is it Safe to Export Networks from Data Lakes?cited by 2
  33. 2023Secure and Fast Asynchronous Vertical Federated Learning via Cascaded Hybrid Optimizationcited by 2
  34. 2023Privacy Preserving Federated Learning with Convolutional Variational Bottleneckscited by 2
  35. 2023Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verificationcited by 2
  36. 2023Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environmentscited by 2
  37. 2024GI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledgecited by 2
  38. 2024Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomycited by 2

50 most cited of 76 All 76 (JSON)