# Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data

arXiv: https://arxiv.org/abs/1911.07101 · HTML: https://mlsanity.com/paper/1911.07101/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2019.

## Built on by (most cited first, 28 of 28)

- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [Differential Privacy for Text Analytics via Natural Text Sanitization](https://mlsanity.com/paper/2106.01221/) (2021)
- [Privacy-Preserving Machine Learning: Methods, Challenges and Directions](https://mlsanity.com/paper/2108.04417/) (2021)
- [SIRNN: A Math Library for Secure RNN Inference](https://mlsanity.com/paper/2105.04236/) (2021)
- [Secure Quantized Training for Deep Learning](https://mlsanity.com/paper/2107.00501/) (2021)
- [A methodology for training homomorphicencryption friendly neural networks](https://mlsanity.com/paper/2111.03362/) (2021)
- [CipherPrune: Efficient and Scalable Private Transformer Inference](https://mlsanity.com/paper/2502.16782/) (2025)
- [GuardML: Efficient Privacy-Preserving Machine Learning Services Through Hybrid Homomorphic Encryption](https://mlsanity.com/paper/2401.14840/) (2024)
- [Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption](https://mlsanity.com/paper/2505.07329/) (2025)
- [Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimation](https://mlsanity.com/paper/2106.02203/) (2021)
- [TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation](https://mlsanity.com/paper/2503.12217/) (2025)
- [CryptoTrain: Fast Secure Training on Encrypted Dataset](https://mlsanity.com/paper/2409.16675/) (2024)
- [RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis](https://mlsanity.com/paper/2502.18517/) (2025)
- [MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption](https://mlsanity.com/paper/2401.09604/) (2024)
- [Neural Network Training on Encrypted Data with TFHE](https://mlsanity.com/paper/2401.16136/) (2024)
- [ReBoot: Encrypted Training of Deep Neural Networks with CKKS Bootstrapping](https://mlsanity.com/paper/2506.19693/) (2025)
- [SoK: Data Minimization in Machine Learning](https://mlsanity.com/paper/2508.10836/) (2025)
- [DictPFL: Efficient and Private Federated Learning on Encrypted Gradients](https://mlsanity.com/paper/2510.21086/) (2025)
- [Protecting Data from all Parties: Combining FHE and DP in Federated Learning](https://mlsanity.com/paper/2205.04330/) (2022)
- [Data Privacy with Homomorphic Encryption in Neural Networks Training and Inference](https://mlsanity.com/paper/2305.02225/) (2023)
- [SABLE: Secure And Byzantine robust LEarning](https://mlsanity.com/paper/2309.05395/) (2023)
- [Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption](https://mlsanity.com/paper/2310.02563/) (2023)
- [I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption](https://mlsanity.com/paper/2402.09059/) (2024)
- [Homomorphic WiSARDs: Efficient Weightless Neural Network training over encrypted data](https://mlsanity.com/paper/2403.20190/) (2024)
- [Functional Encryption in Secure Neural Network Training: Data Leakage and Practical Mitigations](https://mlsanity.com/paper/2509.21497/) (2025)
- [Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs](https://mlsanity.com/paper/2601.05635/) (2026)
- [Detecting and Understanding Vulnerabilities in Fully Homomorphic Encryption Frameworks](https://mlsanity.com/paper/2606.22519/) (2026)
- [Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations](https://mlsanity.com/paper/2608.27066/) (2026)

## Abstract (arXiv)

Big data is one of the cornerstones to enabling and training deep neural networks (DNNs). Because of the lack of expertise, to gain benefits from their data, average users have to rely on and upload their private data to big data companies they may not trust. Due to the compliance, legal, or privacy constraints, most users are willing to contribute only their encrypted data, and lack interests or resources to join the training of DNNs in cloud. To train a DNN on encrypted data in a completely non-interactive way, a recent work proposes a fully homomorphic encryption (FHE)-based technique implementing all activations in the neural network by textitBrakerski-Gentry-Vaikuntanathan (BGV)-based lookup tables. However, such inefficient lookup-table-based activations significantly prolong the training latency of privacy-preserving DNNs. In this paper, we propose, Glyph, a FHE-based scheme to fast and accurately train DNNs on encrypted data by switching between TFHE (Fast Fully Homomorphic Encryption over the Torus) and BGV cryptosystems. Glyph uses logic-operation-friendly TFHE to implement nonlinear activations, while adopts vectorial-arithmetic-friendly BGV to perform multiply-accumulation (MAC) operations. Glyph further applies transfer learning on the training of DNNs to improve the test accuracy and reduce the number of MAC operations between ciphertext and ciphertext in convolutional layers. Our experimental results show Glyph obtains the state-of-the-art test accuracy, but reduces the training latency by 99% over the prior FHE-based technique on various encrypted datasets.