# Partially Encrypted Machine Learning using Functional Encryption

arXiv: https://arxiv.org/abs/1905.10214 · HTML: https://mlsanity.com/paper/1905.10214/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

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

- [Privacy-Preserving Machine Learning: Methods, Challenges and Directions](https://mlsanity.com/paper/2108.04417/) (2021)
- [pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing](https://mlsanity.com/paper/2201.09186/) (2022)
- [Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration](https://mlsanity.com/paper/2205.01423/) (2022)
- [Privacy-Preserving Diffusion Model Using Homomorphic Encryption](https://mlsanity.com/paper/2403.05794/) (2024)
- [SoK: Privacy Preserving Machine Learning using Functional Encryption: Opportunities and Challenges](https://mlsanity.com/paper/2204.05136/) (2022)
- [Private Facial Diagnosis as an Edge Service for Parkinson's DBS Treatment Valuation](https://mlsanity.com/paper/2105.07533/) (2021)

## Abstract (arXiv)

Machine learning on encrypted data has received a lot of attention thanks to recent breakthroughs in homomorphic encryption and secure multi-party computation. It allows outsourcing computation to untrusted servers without sacrificing privacy of sensitive data. We propose a practical framework to perform partially encrypted and privacy-preserving predictions which combines adversarial training and functional encryption. We first present a new functional encryption scheme to efficiently compute quadratic functions so that the data owner controls what can be computed but is not involved in the calculation: it provides a decryption key which allows one to learn a specific function evaluation of some encrypted data. We then show how to use it in machine learning to partially encrypt neural networks with quadratic activation functions at evaluation time, and we provide a thorough analysis of the information leaks based on indistinguishability of data items of the same label. Last, since most encryption schemes cannot deal with the last thresholding operation used for classification, we propose a training method to prevent selected sensitive features from leaking, which adversarially optimizes the network against an adversary trying to identify these features. This is interesting for several existing works using partially encrypted machine learning as it comes with little reduction on the model's accuracy and significantly improves data privacy.