# Fully Homomorphically Encrypted Deep Learning as a Service

arXiv: https://arxiv.org/abs/2107.12997 · HTML: https://mlsanity.com/paper/2107.12997/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 35 references that are in the map.
- First posted on arXiv 26 Jul 2021.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [1D Convolutional Neural Networks and Applications: A Survey](https://mlsanity.com/paper/1905.03554/) (2019)
- [Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network](https://mlsanity.com/paper/2106.07229/) (2021)
- [Classification of Time-Series Images Using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1710.00886/) (2017)
- [On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks](https://mlsanity.com/paper/2011.05530/) (2020)
- [The Role of Cross-Silo Federated Learning in Facilitating Data Sharing in the Agri-Food Sector](https://mlsanity.com/paper/2104.07468/) (2021)
- [Using Deep Learning to Predict Plant Growth and Yield in Greenhouse Environments](https://mlsanity.com/paper/1907.00624/) (2019)
- [An autoencoder wavelet based deep neural network with attention mechanism for multistep prediction of plant growth](https://mlsanity.com/paper/2012.04041/) (2020)

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

- [SLIP: Securing LLMs IP Using Weights Decomposition](https://mlsanity.com/paper/2407.10886/) (2024)
- [Premonition Net, A Multi-Timeline Transformer Network Architecture Towards Strawberry Tabletop Yield Forecasting](https://mlsanity.com/paper/2211.08177/) (2022)
- [HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inference](https://mlsanity.com/paper/2401.15970/) (2024)
- [EDLaaS: Fully Homomorphic Encryption Over Neural Network Graphs for Vision and Private Strawberry Yield Forecasting](https://mlsanity.com/paper/2110.13638/) (2021)
- [Data Privacy with Homomorphic Encryption in Neural Networks Training and Inference](https://mlsanity.com/paper/2305.02225/) (2023)
- [Enhancing Strawberry Yield Forecasting with Backcasted IoT Sensor Data and Machine Learning](https://mlsanity.com/paper/2504.18451/) (2025)

## Abstract (arXiv)

Fully Homomorphic Encryption (FHE) is a relatively recent advancement in the field of privacy-preserving technologies. FHE allows for the arbitrary depth computation of both addition and multiplication, and thus the application of abelian/polynomial equations, like those found in deep learning algorithms. This project investigates, derives, and proves how FHE with deep learning can be used at scale, with relatively low time complexity, the problems that such a system incurs, and mitigations/solutions for such problems. In addition, we discuss how this could have an impact on the future of data privacy and how it can enable data sharing across various actors in the agri-food supply chain, hence allowing the development of machine learning-based systems. Finally, we find that although FHE incurs a high spatial complexity cost, the time complexity is within expected reasonable bounds, while allowing for absolutely private predictions to be made, in our case for milk yield prediction.