# Defending against Reconstruction Attack in Vertical Federated Learning

arXiv: https://arxiv.org/abs/2107.09898 · HTML: https://mlsanity.com/paper/2107.09898/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 21 Jul 2021.

## Builds on (most cited first, 18 of 18)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity](https://mlsanity.com/paper/1811.12469/) (2018)
- [Distributed Differential Privacy via Shuffling](https://mlsanity.com/paper/1808.01394/) (2018)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware](https://mlsanity.com/paper/1806.03287/) (2018)
- [QUOTIENT: Two-Party Secure Neural Network Training and Prediction](https://mlsanity.com/paper/1907.03372/) (2019)
- [No Peek: A Survey of private distributed deep learning](https://mlsanity.com/paper/1812.03288/) (2018)
- [A fast algorithm for computing distance correlation](https://mlsanity.com/paper/1810.11332/) (2018)
- [Learning Anonymized Representations with Adversarial Neural Networks](https://mlsanity.com/paper/1802.09386/) (2018)
- [A Statistically and Numerically Efficient Independence Test based on Random Projections and Distance Covariance](https://mlsanity.com/paper/1701.06054/) (2017)
- [A Review of Homomorphic Encryption Libraries for Secure Computation](https://mlsanity.com/paper/1812.02428/) (2018)

## Built on by (most cited first, 20 of 20)

- [Vertical Federated Learning: Concepts, Advances and Challenges](https://mlsanity.com/paper/2211.12814/) (2022)
- [A Survey on Vertical Federated Learning: From a Layered Perspective](https://mlsanity.com/paper/2304.01829/) (2023)
- [Label Leakage and Protection from Forward Embedding in Vertical Federated Learning](https://mlsanity.com/paper/2203.01451/) (2022)
- [Vertical Federated Learning: A Structured Literature Review](https://mlsanity.com/paper/2212.00622/) (2022)
- [Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey](https://mlsanity.com/paper/2405.17495/) (2024)
- [HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning](https://mlsanity.com/paper/2212.00325/) (2022)
- [Label Inference Attack against Split Learning under Regression Setting](https://mlsanity.com/paper/2301.07284/) (2023)
- [VFLAIR: A Research Library and Benchmark for Vertical Federated Learning](https://mlsanity.com/paper/2310.09827/) (2023)
- [DPAUC: Differentially Private AUC Computation in Federated Learning](https://mlsanity.com/paper/2208.12294/) (2022)
- [Advancements in Federated Learning: Models, Methods, and Privacy](https://mlsanity.com/paper/2302.11466/) (2023)
- [A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective](https://mlsanity.com/paper/2402.03688/) (2024)
- [FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learning](https://mlsanity.com/paper/2305.08328/) (2023)
- [Online Vertical Federated Learning for Cooperative Spectrum Sensing](https://mlsanity.com/paper/2312.11363/) (2023)
- [A Survey on Contribution Evaluation in Vertical Federated Learning](https://mlsanity.com/paper/2405.02364/) (2024)
- [Differentially Private Vertical Federated Learning](https://mlsanity.com/paper/2211.06782/) (2022)
- [Differentially Private AUC Computation in Vertical Federated Learning](https://mlsanity.com/paper/2205.12412/) (2022)
- [URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning](https://mlsanity.com/paper/2404.19582/) (2024)
- [Just a Simple Transformation is Enough for Data Protection in Vertical Federated Learning](https://mlsanity.com/paper/2412.11689/) (2024)
- [Survey of Privacy Threats and Countermeasures in Federated Learning](https://mlsanity.com/paper/2402.00342/) (2024)
- [Computation and Communication Efficient Lightweighting Vertical Federated Learning for Smart Building IoT](https://mlsanity.com/paper/2404.00466/) (2024)

## 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.