mlsanityData to 7 Oct 2026

Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning

arXiv 2210.06771 ↗First posted 13 Oct 2022cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has increasingly been deployed, in its vertical form, among organizations to facilitate secure collaborative training over siloed data. In vertical FL (VFL), participants hold disjoint features of the same set of sample instances. Among them, only one has labels. This participant, known as the active party, initiates the training and interacts with the other participants, known as the passive parties. Despite the increasing adoption of VFL, it remains largely unknown if and how the active party can extract feature data from the passive party, especially when training deep neural network (DNN) models. This paper makes the first attempt to study the feature security problem of DNN training in VFL. We consider a DNN model partitioned between active and passive parties, where the latter only holds a subset of the input layer and exhibits some categorical features of binary values. Using a reduction from the Exact Cover problem, we prove that reconstructing those binary features is NP-hard. Through analysis, we demonstrate that, unless the feature dimension is exceedingly large, it remains feasible, both theoretically and practically, to launch a reconstruction attack with an efficient search-based algorithm that prevails over current feature protection techniques. To address this problem, we develop a novel feature protection scheme against the reconstruction attack that effectively misleads the search to some pre-specified random values. With an extensive set of experiments, we show that our protection scheme sustains the feature reconstruction attack in various VFL applications at no expense of accuracy loss.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 14 of its 37 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

14 of 37 references.

References · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  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. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  6. 2021Distilling Knowledge via Knowledge Reviewcited by 285
  7. 2018Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learningcited by 211
  8. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
  9. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 174
  10. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 105
  11. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  12. 2022BlindFL: Vertical Federated Machine Learning without Peeking into Your Datacited by 36
2 more
  1. 2021PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNNcited by 35
  2. 2021Batch Label Inference and Replacement Attacks in Black-Boxed Vertical Federated Learningcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 4; 2025: 3; 2026: 1.

13 papers.

Sort:

By area:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  2. 2022Vertical Federated Learning: A Structured Literature Reviewcited by 17
  3. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  4. 2024A Survey on Intelligent Internet of Things: Applications, Security, Privacy, and Future Directionscited by 10
  5. 2023VFLAIR: A Research Library and Benchmark for Vertical Federated Learningcited by 8
  6. 2024A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspectivecited by 7
  7. 2023Mutual Information Regularization for Vertical Federated Learningcited by 3
  8. 2023Flexible Differentially Private Vertical Federated Learning with Adaptive Feature Embeddingscited by 1
  9. 2024Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learningcited by 1
  10. 2025A Distributed Generative AI Approach for Heterogeneous Multi-Domain Environments under Data Sharing constraintscited by 1
  11. 2025Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimizationcited by 0
  12. 2025Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigmscited by 0
1 more
  1. 2026CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learningcited by 0