mlsanityData to 7 Oct 2026

Defending against Reconstruction Attack in Vertical Federated Learning

arXiv 2107.09898 ↗First posted 21 Jul 2021cs.LG cs.CRcited by 20

Not on the map. Why?

Abstract (arXiv)

Recently researchers have studied input leakage problems in Federated Learning (FL) where a malicious party can reconstruct sensitive training inputs provided by users from shared gradient. It raises concerns about FL since input leakage contradicts the privacy-preserving intention of using FL. Despite a relatively rich literature on attacks and defenses of input reconstruction in Horizontal FL, input leakage and protection in vertical FL starts to draw researcher's attention recently. In this paper, we study how to defend against input leakage attacks in Vertical FL. We design an adversarial training-based framework that contains three modules: adversarial reconstruction, noise regularization, and distance correlation minimization. Those modules can not only be employed individually but also applied together since they are independent to each other. Through extensive experiments on a large-scale industrial online advertising dataset, we show our framework is effective in protecting input privacy while retaining the model utility.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 21 Jul 2021.

Builds on

18 of 26 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2016Wide & Deep Learning for Recommender Systemscited by 745
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  7. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  8. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  9. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 163
  10. 2018Distributed Differential Privacy via Shufflingcited by 115
  11. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 105
  12. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 101
6 more
  1. 2019QUOTIENT: Two-Party Secure Neural Network Training and Predictioncited by 41
  2. 2018No Peek: A Survey of private distributed deep learningcited by 30
  3. 2018A fast algorithm for computing distance correlationcited by 8
  4. 2018Learning Anonymized Representations with Adversarial Neural Networkscited by 7
  5. 2017A Statistically and Numerically Efficient Independence Test based on Random Projections and Distance Covariancecited by 4
  6. 2018A Review of Homomorphic Encryption Libraries for Secure Computationcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 7; 2023: 6; 2024: 7.

20 papers.

Sort:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  2. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  3. 2022Label Leakage and Protection from Forward Embedding in Vertical Federated Learningcited by 26
  4. 2022Vertical Federated Learning: A Structured Literature Reviewcited by 17
  5. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  6. 2022HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learningcited by 10
  7. 2023VFLAIR: A Research Library and Benchmark for Vertical Federated Learningcited by 8
  8. 2022DPAUC: Differentially Private AUC Computation in Federated Learningcited by 7
  9. 2023Label Inference Attack against Split Learning under Regression Settingcited by 7
  10. 2023Advancements in Federated Learning: Models, Methods, and Privacycited by 7
  11. 2024A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspectivecited by 7
  12. 2023FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learningcited by 6
8 more
  1. 2023Online Vertical Federated Learning for Cooperative Spectrum Sensingcited by 6
  2. 2024A Survey on Contribution Evaluation in Vertical Federated Learningcited by 5
  3. 2022Differentially Private Vertical Federated Learningcited by 4
  4. 2022Differentially Private AUC Computation in Vertical Federated Learningcited by 3
  5. 2024URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learningcited by 3
  6. 2024Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learningcited by 1
  7. 2024Survey of Privacy Threats and Countermeasures in Federated Learningcited by 0
  8. 2024Computation and Communication Efficient Lightweighting Vertical Federated Learning for Smart Building IoTcited by 0