mlsanityData to 14 Oct 2026

A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective

arXiv 2402.03688 ↗First posted 6 Feb 2024cs.CR cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Vertical Federated Learning (VFL) is a federated learning paradigm where multiple participants, who share the same set of samples but hold different features, jointly train machine learning models. Although VFL enables collaborative machine learning without sharing raw data, it is still susceptible to various privacy threats. In this paper, we conduct the first comprehensive survey of the state-of-the-art in privacy attacks and defenses in VFL. We provide taxonomies for both attacks and defenses, based on their characterizations, and discuss open challenges and future research directions. Specifically, our discussion is structured around the model's life cycle, by delving into the privacy threats encountered during different stages of machine learning and their corresponding countermeasures. This survey not only serves as a resource for the research community but also offers clear guidance and actionable insights for practitioners to safeguard data privacy throughout the model's life cycle.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 86 of its 177 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

86 of 177 references.

References · 86

  1. 2019Advances and Open Problems in Federated Learningcited by 3,046
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  4. 2019Deep Leakage from Gradientscited by 1,021
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  6. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  7. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  8. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  9. 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
  10. 2018Distributed learning of deep neural network over multiple agentscited by 279
  11. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 218
  12. 2020Threats to Federated Learning: A Surveycited by 178
38 more
  1. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  2. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
  3. 2021Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradientscited by 123
  4. 2021Deep Learning with Label Differential Privacycited by 117
  5. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  6. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  7. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
  8. 2021Label Leakage and Protection in Two-party Split Learningcited by 90
  9. 2020Privacy Preserving Vertical Federated Learning for Tree-based Modelscited by 89
  10. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  11. 2020Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approachcited by 81
  12. 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 77
  13. 2021CAFE: Catastrophic Data Leakage in Vertical Federated Learningcited by 76
  14. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  15. 2014On the Computational Efficiency of Training Neural Networkscited by 71
  16. 2018Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacycited by 66
  17. 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
  18. 2020Vertically Federated Graph Neural Network for Privacy-Preserving Node Classificationcited by 61
  19. 2022Vertical Federated Learning: Challenges, Methodologies and Experimentscited by 55
  20. 2019Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinatorcited by 52
  21. 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
  22. 2020Local Differential Privacy and Its Applications: A Comprehensive Surveycited by 41
  23. 2019A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regressioncited by 38
  24. 2021Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updatingcited by 37
  25. 2020Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Datacited by 36
  26. 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
  27. 2022BlindFL: Vertical Federated Machine Learning without Peeking into Your Datacited by 36
  28. 2023One-shot Empirical Privacy Estimation for Federated Learningcited by 36
  29. 2021PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNNcited by 35
  30. 2020When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Controlcited by 32
  31. 2021FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Datacited by 31
  32. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  33. 2021Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretabilitycited by 28
  34. 2020FederBoost: Private Federated Learning for GBDTcited by 27
  35. 2022Label Leakage and Protection from Forward Embedding in Vertical Federated Learningcited by 27
  36. 2020Asymmetrical Vertical Federated Learningcited by 26
  37. 2020Large-Scale Secure XGB for Vertical Federated Learningcited by 26
  38. 2022Differentially Private Label Protection in Split Learningcited by 26

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 1.

7 papers.

  1. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  2. 2024Vertical Federated Learning with Missing Features During Training and Inferencecited by 6
  3. 2025Vertical Federated Learning in Practice: The Good, the Bad, and the Uglycited by 4
  4. 2025Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learningcited by 3
  5. 2025Tree-based Models for Vertical Federated Learning: A Surveycited by 3
  6. 2024Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learningcited by 1
  7. 2026Toward Reliable, Safe, and Secure LLMs for Scientific Applicationscited by 1