# TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecture

arXiv: https://arxiv.org/abs/2302.01584 · HTML: https://mlsanity.com/paper/2302.01584/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 65 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [PRADA: Protecting against DNN Model Stealing Attacks](https://mlsanity.com/paper/1805.02628/) (2018)
- [Cryptanalytic Extraction of Neural Network Models](https://mlsanity.com/paper/2003.04884/) (2020)
- [Low Latency Privacy Preserving Inference](https://mlsanity.com/paper/1812.10659/) (2018)
- [Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data](https://mlsanity.com/paper/2011.03274/) (2020)
- [XONN: XNOR-based Oblivious Deep Neural Network Inference](https://mlsanity.com/paper/1902.07342/) (2019)
- [CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU](https://mlsanity.com/paper/2104.10949/) (2021)
- [Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference](https://mlsanity.com/paper/1811.09953/) (2018)
- [Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data](https://mlsanity.com/paper/2101.08030/) (2021)
- [Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Data](https://mlsanity.com/paper/2012.15330/) (2020)
- [SHE: A Fast and Accurate Deep Neural Network for Encrypted Data](https://mlsanity.com/paper/1906.00148/) (2019)
- [Generalized Linear Rule Models](https://mlsanity.com/paper/1906.01761/) (2019)
- [nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data](https://mlsanity.com/paper/1810.10121/) (2018)
- [TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service](https://mlsanity.com/paper/1806.03461/) (2018)
- [Private and Reliable Neural Network Inference](https://mlsanity.com/paper/2210.15614/) (2022)

## Built on by (most cited first, 4 of 4)

- [DCT-CryptoNets: Scaling Private Inference in the Frequency Domain](https://mlsanity.com/paper/2408.15231/) (2024)
- [Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks](https://mlsanity.com/paper/2604.16834/) (2026)
- [Encrypted Neural Networks without Overflows](https://mlsanity.com/paper/2605.23096/) (2026)
- [EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE](https://mlsanity.com/paper/2609.13636/) (2026)

## Abstract (arXiv)

This paper presents TT-TFHE, a deep neural network Fully Homomorphic Encryption (FHE) framework that effectively scales Torus FHE (TFHE) usage to tabular and image datasets using a recent family of convolutional neural networks called Truth-Table Neural Networks (TTnet). The proposed framework provides an easy-to-implement, automated TTnet-based design toolbox with an underlying (python-based) open-source Concrete implementation (CPU-based and implementing lookup tables) for inference over encrypted data. Experimental evaluation shows that TT-TFHE greatly outperforms in terms of time and accuracy all Homomorphic Encryption (HE) set-ups on three tabular datasets, all other features being equal. On image datasets such as MNIST and CIFAR-10, we show that TT-TFHE consistently and largely outperforms other TFHE set-ups and is competitive against other HE variants such as BFV or CKKS (while maintaining the same level of 128-bit encryption security guarantees). In addition, our solutions present a very low memory footprint (down to dozens of MBs for MNIST), which is in sharp contrast with other HE set-ups that typically require tens to hundreds of GBs of memory per user (in addition to their communication overheads). This is the first work presenting a fully practical solution of private inference (i.e. a few seconds for inference time and a few dozens MBs of memory) on both tabular datasets and MNIST, that can easily scale to multiple threads and users on server side.