mlsanityData to 7 Oct 2026

Deep Neural Networks for Encrypted Inference with TFHE

arXiv 2302.10906 ↗First posted 13 Feb 2023cs.LG cs.AI cs.CRcited by 11

Not on the map. Why?

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.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 3 of its 15 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

3 of 15 references.

References · 3

  1. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  2. 2019SHE: A Fast and Accurate Deep Neural Network for Encrypted Datacited by 36
  3. 2022SPIQ: Data-Free Per-Channel Static Input Quantizationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 1; 2026: 3.

11 papers.

  1. 2023A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidancecited by 11
  2. 2024A2Q+: Improving Accumulator-Aware Weight Quantizationcited by 5
  3. 2024Accumulator-Aware Post-Training Quantization for Large Language Modelscited by 4
  4. 2023Inhibitor Transformers and Gated RNNs for Torus Efficient Fully Homomorphic Encryptioncited by 2
  5. 2024DCT-CryptoNets: Scaling Private Inference in the Frequency Domaincited by 1
  6. 2024Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Launderingcited by 1
  7. 2024Privacy-Preserving Intrusion Detection using Convolutional Neural Networkscited by 0
  8. 2025Fortytwo: Swarm Inference with Peer-Ranked Consensuscited by 0
  9. 2026Robust Federated Learning via Byzantine Filtering over Encrypted Updatescited by 0
  10. 2026EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHEcited by 0
  11. 2026OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-designcited by 0