# Deep Neural Networks for Encrypted Inference with TFHE

arXiv: https://arxiv.org/abs/2302.10906 · HTML: https://mlsanity.com/paper/2302.10906/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 15 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 3 of 3)

- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [SHE: A Fast and Accurate Deep Neural Network for Encrypted Data](https://mlsanity.com/paper/1906.00148/) (2019)
- [SPIQ: Data-Free Per-Channel Static Input Quantization](https://mlsanity.com/paper/2203.14642/) (2022)

## Built on by (most cited first, 11 of 11)

- [A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance](https://mlsanity.com/paper/2308.13504/) (2023)
- [Accumulator-Aware Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2409.17092/) (2024)
- [A2Q+: Improving Accumulator-Aware Weight Quantization](https://mlsanity.com/paper/2401.10432/) (2024)
- [Inhibitor Transformers and Gated RNNs for Torus Efficient Fully Homomorphic Encryption](https://mlsanity.com/paper/2308.05629/) (2023)
- [DCT-CryptoNets: Scaling Private Inference in the Frequency Domain](https://mlsanity.com/paper/2408.15231/) (2024)
- [Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering](https://mlsanity.com/paper/2411.02926/) (2024)
- [Privacy-Preserving Intrusion Detection using Convolutional Neural Networks](https://mlsanity.com/paper/2404.09625/) (2024)
- [Fortytwo: Swarm Inference with Peer-Ranked Consensus](https://mlsanity.com/paper/2510.24801/) (2025)
- [Robust Federated Learning via Byzantine Filtering over Encrypted Updates](https://mlsanity.com/paper/2602.05410/) (2026)
- [EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE](https://mlsanity.com/paper/2609.13636/) (2026)
- [OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design](https://mlsanity.com/paper/2609.16898/) (2026)

## Abstract (arXiv)

Fully homomorphic encryption (FHE) is an encryption method that allows to perform computation on encrypted data, without decryption. FHE preserves the privacy of the users of online services that handle sensitive data, such as health data, biometrics, credit scores and other personal information. A common way to provide a valuable service on such data is through machine learning and, at this time, Neural Networks are the dominant machine learning model for unstructured data. In this work we show how to construct Deep Neural Networks (DNN) that are compatible with the constraints of TFHE, an FHE scheme that allows arbitrary depth computation circuits. We discuss the constraints and show the architecture of DNNs for two computer vision tasks. We benchmark the architectures using the Concrete stack, an open-source implementation of TFHE.