# Privacy-Preserving Deep Learning via Weight Transmission

arXiv: https://arxiv.org/abs/1809.03272 · HTML: https://mlsanity.com/paper/1809.03272/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications](https://mlsanity.com/paper/2201.11006/) (2022)
- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [Trustworthy Privacy-preserving Hierarchical Ensemble and Federated Learning in Healthcare 4.0 with Blockchain](https://mlsanity.com/paper/2305.09209/) (2023)
- [A Privacy-Preserving Outsourced Data Model in Cloud Environment](https://mlsanity.com/paper/2211.13542/) (2022)
- [Efficient Core-selecting Incentive Mechanism for Data Sharing in Federated Learning](https://mlsanity.com/paper/2309.11722/) (2023)
- [Asyn2F: An Asynchronous Federated Learning Framework with Bidirectional Model Aggregation](https://mlsanity.com/paper/2403.01417/) (2024)
- [Reliability Check via Weight Similarity in Privacy-Preserving Multi-Party Machine Learning](https://mlsanity.com/paper/2101.05504/) (2021)
- [Privacy-Preserving Ensemble Infused Enhanced Deep Neural Network Framework for Edge Cloud Convergence](https://mlsanity.com/paper/2305.09224/) (2023)
- [SoK: A Systematic Bidirectional Literature Review of AI & DLT Convergence](https://mlsanity.com/paper/2605.10515/) (2026)

## Abstract (arXiv)

This paper considers the scenario that multiple data owners wish to apply a machine learning method over the combined dataset of all owners to obtain the best possible learning output but do not want to share the local datasets owing to privacy concerns. We design systems for the scenario that the stochastic gradient descent (SGD) algorithm is used as the machine learning method because SGD (or its variants) is at the heart of recent deep learning techniques over neural networks. Our systems differ from existing systems in the following features: bf (1) any activation function can be used, meaning that no privacy-preserving-friendly approximation is required; bf (2) gradients computed by SGD are not shared but the weight parameters are shared instead; and bf (3) robustness against colluding parties even in the extreme case that only one honest party exists. We prove that our systems, while privacy-preserving, achieve the same learning accuracy as SGD and hence retain the merit of deep learning with respect to accuracy. Finally, we conduct several experiments using benchmark datasets, and show that our systems outperform previous system in terms of learning accuracies.