# nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data

arXiv: https://arxiv.org/abs/1810.10121 · HTML: https://mlsanity.com/paper/1810.10121/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2018.

## Built on by (most cited first, 24 of 24)

- [Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network](https://mlsanity.com/paper/2106.07229/) (2021)
- [THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption](https://mlsanity.com/paper/2206.00216/) (2022)
- [TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption](https://mlsanity.com/paper/2104.03152/) (2021)
- [CaPC Learning: Confidential and Private Collaborative Learning](https://mlsanity.com/paper/2102.05188/) (2021)
- [SIRNN: A Math Library for Secure RNN Inference](https://mlsanity.com/paper/2105.04236/) (2021)
- [Private and Reliable Neural Network Inference](https://mlsanity.com/paper/2210.15614/) (2022)
- [Enabling Homomorphically Encrypted Inference for Large DNN Models](https://mlsanity.com/paper/2103.16139/) (2021)
- [Privacy-Preserving Diffusion Model Using Homomorphic Encryption](https://mlsanity.com/paper/2403.05794/) (2024)
- [TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecture](https://mlsanity.com/paper/2302.01584/) (2023)
- [Optimized Layerwise Approximation for Efficient Private Inference on Fully Homomorphic Encryption](https://mlsanity.com/paper/2310.10349/) (2023)
- [SoK: Privacy-preserving Deep Learning with Homomorphic Encryption](https://mlsanity.com/paper/2112.12855/) (2021)
- [Efficient ML Models for Practical Secure Inference](https://mlsanity.com/paper/2209.00411/) (2022)
- [Hyperdimensional Computing as a Rescue for Efficient Privacy-Preserving Machine Learning-as-a-Service](https://mlsanity.com/paper/2310.06840/) (2023)
- [FFConv: Fast Factorized Convolutional Neural Network Inference on Encrypted Data](https://mlsanity.com/paper/2102.03494/) (2021)
- [Privacy-Preserving Distributed Machine Learning Made Faster](https://mlsanity.com/paper/2205.05825/) (2022)
- [Partially Oblivious Neural Network Inference](https://mlsanity.com/paper/2210.15189/) (2022)
- [HE-MAN -- Homomorphically Encrypted MAchine learning with oNnx models](https://mlsanity.com/paper/2302.08260/) (2023)
- [Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvement](https://mlsanity.com/paper/2402.11224/) (2024)
- [A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism](https://mlsanity.com/paper/2403.07283/) (2024)
- [Privacy-Preserving Hierarchical Model-Distributed Inference](https://mlsanity.com/paper/2407.18353/) (2024)
- [ALT: Boosting Deep Learning Performance by Breaking the Wall between Graph and Operator Level Optimizations](https://mlsanity.com/paper/2210.12415/) (2022)
- [SFPDML: Securer and Faster Privacy-Preserving Distributed Machine Learning based on MKTFHE](https://mlsanity.com/paper/2211.09353/) (2022)
- [Towards Automated Homomorphic Encryption Parameter Selection with Fuzzy Logic and Linear Programming](https://mlsanity.com/paper/2302.08930/) (2023)
- [SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy](https://mlsanity.com/paper/2601.09460/) (2026)

## Abstract (arXiv)

Homomorphic encryption (HE)---the ability to perform computation on encrypted data---is an attractive remedy to increasing concerns about data privacy in deep learning (DL). However, building DL models that operate on ciphertext is currently labor-intensive and requires simultaneous expertise in DL, cryptography, and software engineering. DL frameworks and recent advances in graph compilers have greatly accelerated the training and deployment of DL models to various computing platforms. We introduce nGraph-HE, an extension of nGraph, Intel's DL graph compiler, which enables deployment of trained models with popular frameworks such as TensorFlow while simply treating HE as another hardware target. Our graph-compiler approach enables HE-aware optimizations-- implemented at compile-time, such as constant folding and HE-SIMD packing, and at run-time, such as special value plaintext bypass. Furthermore, nGraph-HE integrates with DL frameworks such as TensorFlow, enabling data scientists to benchmark DL models with minimal overhead.