mlsanityData to 14 Oct 2026

URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning

arXiv 2404.19582 ↗First posted 30 Apr 2024cs.LG cs.CRcited by 3

Not on the map. Why?

Abstract (arXiv)

Launching effective malicious attacks in VFL presents unique challenges: 1) Firstly, given the distributed nature of clients' data features and models, each client rigorously guards its privacy and prohibits direct querying, complicating any attempts to steal data; 2) Existing malicious attacks alter the underlying VFL training task, and are hence easily detected by comparing the received gradients with the ones received in honest training. To overcome these challenges, we develop URVFL, a novel attack strategy that evades current detection mechanisms. The key idea is to integrate a discriminator with auxiliary classifier that takes a full advantage of the label information and generates malicious gradients to the victim clients: on one hand, label information helps to better characterize embeddings of samples from distinct classes, yielding an improved reconstruction performance; on the other hand, computing malicious gradients with label information better mimics the honest training, making the malicious gradients indistinguishable from the honest ones, and the attack much more stealthy. Our comprehensive experiments demonstrate that URVFL significantly outperforms existing attacks, and successfully circumvents SOTA detection methods for malicious attacks. Additional ablation studies and evaluations on defenses further underscore the robustness and effectiveness of URVFL. Our code will be available at https://github.com/duanyiyao/URVFL.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

27 of 49 references.

References · 27

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  4. 2021Towards Personalized Federated Learningcited by 464
  5. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  6. 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
  7. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
  8. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  9. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 105
  10. 2020Privacy Preserving Vertical Federated Learning for Tree-based Modelscited by 89
  11. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  12. 2019Split Learning for collaborative deep learning in healthcarecited by 73
15 more
  1. 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
  2. 2021UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learningcited by 52
  3. 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
  4. 2020Multi-Participant Multi-Class Vertical Federated Learningcited by 47
  5. 2019A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regressioncited by 38
  6. 2022BlindFL: Vertical Federated Machine Learning without Peeking into Your Datacited by 36
  7. 2020Hybrid Differentially Private Federated Learning on Vertically Partitioned Datacited by 22
  8. 2021Defending against Reconstruction Attack in Vertical Federated Learningcited by 20
  9. 2021Conditional GANs with Auxiliary Discriminative Classifiercited by 20
  10. 2021SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learningcited by 20
  11. 2023FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Modelscited by 17
  12. 2023Passive Inference Attacks on Split Learning via Adversarial Regularizationcited by 9
  13. 2020Multiple Classification with Split Learningcited by 6
  14. 2021Efficient Batch Homomorphic Encryption for Vertically Federated XGBoostcited by 6
  15. 2022EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third Partycited by 5

Built on by

Cited by year (2026 to 14 Oct)

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

3 papers.

  1. 2025From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challengescited by 4
  2. 2025GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Modelscited by 1
  3. 2026CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learningcited by 0