# Secure Forward Aggregation for Vertical Federated Neural Networks

arXiv: https://arxiv.org/abs/2207.00165 · HTML: https://mlsanity.com/paper/2207.00165/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 28 Jun 2022.

## Builds on (most cited first, 11 of 11)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Split learning for health: Distributed deep learning without sharing raw patient data](https://mlsanity.com/paper/1812.00564/) (2018)
- [Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption](https://mlsanity.com/paper/1711.10677/) (2017)
- [SecureBoost: A Lossless Federated Learning Framework](https://mlsanity.com/paper/1901.08755/) (2019)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating](https://mlsanity.com/paper/2103.00958/) (2021)
- [HAFLO: GPU-Based Acceleration for Federated Logistic Regression](https://mlsanity.com/paper/2107.13797/) (2021)

## Built on by (most cited first, 6 of 6)

- [A Survey on Vertical Federated Learning: From a Layered Perspective](https://mlsanity.com/paper/2304.01829/) (2023)
- [FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models](https://mlsanity.com/paper/2304.13407/) (2023)
- [Secure Vertical Federated Learning Under Unreliable Connectivity](https://mlsanity.com/paper/2305.16794/) (2023)
- [HSTFL: A Heterogeneous Federated Learning Framework for Misaligned Spatiotemporal Forecasting](https://mlsanity.com/paper/2409.18482/) (2024)
- [PackVFL: Efficient HE Packing for Vertical Federated Learning](https://mlsanity.com/paper/2405.00482/) (2024)
- [VMask: Tunable Label Privacy Protection for Vertical Federated Learning via Layer Masking](https://mlsanity.com/paper/2507.14629/) (2025)

## Abstract (arXiv)

Vertical federated learning (VFL) is attracting much attention because it enables cross-silo data cooperation in a privacy-preserving manner. While most research works in VFL focus on linear and tree models, deep models (e.g., neural networks) are not well studied in VFL. In this paper, we focus on SplitNN, a well-known neural network framework in VFL, and identify a trade-off between data security and model performance in SplitNN. Briefly, SplitNN trains the model by exchanging gradients and transformed data. On the one hand, SplitNN suffers from the loss of model performance since multiply parties jointly train the model using transformed data instead of raw data, and a large amount of low-level feature information is discarded. On the other hand, a naive solution of increasing the model performance through aggregating at lower layers in SplitNN (i.e., the data is less transformed and more low-level feature is preserved) makes raw data vulnerable to inference attacks. To mitigate the above trade-off, we propose a new neural network protocol in VFL called Security Forward Aggregation (SFA). It changes the way of aggregating the transformed data and adopts removable masks to protect the raw data. Experiment results show that networks with SFA achieve both data security and high model performance.