mlsanityData to 13 Oct 2026

Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning

arXiv 2412.11689 ↗First posted 16 Dec 2024cs.LG cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

Vertical Federated Learning (VFL) aims to enable collaborative training of deep learning models while maintaining privacy protection. However, the VFL procedure still has components that are vulnerable to attacks by malicious parties. In our work, we consider feature reconstruction attacks, a common risk targeting input data compromise. We theoretically claim that feature reconstruction attacks cannot succeed without knowledge of the prior distribution on data. Consequently, we demonstrate that even simple model architecture transformations can significantly impact the protection of input data during VFL. Confirming these findings with experimental results, we show that MLP-based models are resistant to state-of-the-art feature reconstruction attacks.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 44 of its 77 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

44 of 77 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,082
  4. 2022Generative Adversarial Networkscited by 5,614
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,328
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,981
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,273
  8. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,470
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,442
  10. 2019Deep Leakage from Gradientscited by 1,017
  11. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 711
  12. 2013Generating Sequences With Recurrent Neural Networkscited by 553
32 more
  1. 2020iDLG: Improved Deep Leakage from Gradientscited by 380
  2. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 305
  3. 2018Distributed learning of deep neural network over multiple agentscited by 279
  4. 2020Loss landscapes and optimization in over-parameterized non-linear systems and neural networkscited by 231
  5. 2015Coordinate Descent Algorithmscited by 218
  6. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 218
  7. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  8. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
  9. 2021Deep Learning with Label Differential Privacycited by 116
  10. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  11. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  12. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
  13. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  14. 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
  15. 2020Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Datacited by 36
  16. 2022ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learningcited by 36
  17. 2019Adversarial Neural Network Inversion via Auxiliary Knowledge Alignmentcited by 32
  18. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  19. 2022Label Leakage and Protection from Forward Embedding in Vertical Federated Learningcited by 27
  20. 2021Defending against Reconstruction Attack in Vertical Federated Learningcited by 20
  21. 2021SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learningcited by 20
  22. 2021Batch Label Inference and Replacement Attacks in Black-Boxed Vertical Federated Learningcited by 16
  23. 2022Similarity-based Label Inference Attack against Training and Inference of Split Learningcited by 15
  24. 2022Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learningcited by 13
  25. 2023Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?cited by 13
  26. 2022Differentially Private Vertical Federated Clusteringcited by 10
  27. 2024A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspectivecited by 7
  28. 2022Stochastic Gradient Methods with Preconditioned Updatescited by 5
  29. 2023Model Extraction Attacks on Split Federated Learningcited by 5
  30. 2023SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detectioncited by 4
  31. 2023Secure Vertical Federated Learning Under Unreliable Connectivitycited by 4
  32. 2023Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddingscited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inferencecited by 0