# Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption

arXiv: https://arxiv.org/abs/2310.02563 · HTML: https://mlsanity.com/paper/2310.02563/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 44 references that are in the map.
- First posted on arXiv 4 Oct 2023.

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

- [The Privacy Blanket of the Shuffle Model](https://mlsanity.com/paper/1903.02837/) (2019)
- [The Ladder: A Reliable Leaderboard for Machine Learning Competitions](https://mlsanity.com/paper/1502.04585/) (2015)
- [Prio: Private, Robust, and Scalable Computation of Aggregate Statistics](https://mlsanity.com/paper/1703.06255/) (2017)
- [Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data](https://mlsanity.com/paper/1911.07101/) (2019)
- [Secure Quantized Training for Deep Learning](https://mlsanity.com/paper/2107.00501/) (2021)
- [CryptoNN: Training Neural Networks over Encrypted Data](https://mlsanity.com/paper/1904.07303/) (2019)
- [Making the Most of Parallel Composition in Differential Privacy](https://mlsanity.com/paper/2109.09078/) (2021)
- [Drynx: Decentralized, Secure, Verifiable System for Statistical Queries and Machine Learning on Distributed Datasets](https://mlsanity.com/paper/1902.03785/) (2019)
- [NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets](https://mlsanity.com/paper/2012.10547/) (2020)
- [A Differentially Private Framework for Deep Learning with Convexified Loss Functions](https://mlsanity.com/paper/2204.01049/) (2022)
- [A Survey on Zero Knowledge Range Proofs and Applications](https://mlsanity.com/paper/1907.06381/) (2019)

## Abstract (arXiv)

Two parties wish to collaborate on their datasets. However, before they reveal their datasets to each other, the parties want to have the guarantee that the collaboration would be fruitful. We look at this problem from the point of view of machine learning, where one party is promised an improvement on its prediction model by incorporating data from the other party. The parties would only wish to collaborate further if the updated model shows an improvement in accuracy. Before this is ascertained, the two parties would not want to disclose their models and datasets. In this work, we construct an interactive protocol for this problem based on the fully homomorphic encryption scheme over the Torus (TFHE) and label differential privacy, where the underlying machine learning model is a neural network. Label differential privacy is used to ensure that computations are not done entirely in the encrypted domain, which is a significant bottleneck for neural network training according to the current state-of-the-art FHE implementations. We formally prove the security of our scheme assuming honest-but-curious parties, but where one party may not have any expertise in labelling its initial dataset. Experiments show that we can obtain the output, i.e., the accuracy of the updated model, with time many orders of magnitude faster than a protocol using entirely FHE operations.