# HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture

arXiv: https://arxiv.org/abs/2106.00038 · HTML: https://mlsanity.com/paper/2106.00038/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 7 of 7)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [EVA: An Encrypted Vector Arithmetic Language and Compiler for Efficient Homomorphic Computation](https://mlsanity.com/paper/1912.11951/) (2019)
- [NASS: Optimizing Secure Inference via Neural Architecture Search](https://mlsanity.com/paper/2001.11854/) (2020)
- [AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference](https://mlsanity.com/paper/2006.04219/) (2020)

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

- [Scaling up Trustless DNN Inference with Zero-Knowledge Proofs](https://mlsanity.com/paper/2210.08674/) (2022)
- [Verifiable evaluations of machine learning models using zkSNARKs](https://mlsanity.com/paper/2402.02675/) (2024)
- [AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE](https://mlsanity.com/paper/2310.08012/) (2023)
- [Trustless Audits without Revealing Data or Models](https://mlsanity.com/paper/2404.04500/) (2024)
- [AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference](https://mlsanity.com/paper/2201.06699/) (2022)
- [HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networks](https://mlsanity.com/paper/2302.02407/) (2023)
- [TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks](https://mlsanity.com/paper/2504.19274/) (2025)
- [Private and Reliable Neural Network Inference](https://mlsanity.com/paper/2210.15614/) (2022)
- [Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption](https://mlsanity.com/paper/2304.14836/) (2023)
- [Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inference](https://mlsanity.com/paper/2308.13189/) (2023)
- [ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets](https://mlsanity.com/paper/2407.02960/) (2024)
- [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)
- [Efficient Pruning for Machine Learning Under Homomorphic Encryption](https://mlsanity.com/paper/2207.03384/) (2022)
- [CryptoFace: End-to-End Encrypted Face Recognition](https://mlsanity.com/paper/2509.00332/) (2025)
- [Self-Supervised Inference of Agents in Trustless Environments](https://mlsanity.com/paper/2409.08386/) (2024)
- [Privacy-Preserving Chest X-ray Classification in Latent Space with Homomorphically Encrypted Neural Inference](https://mlsanity.com/paper/2506.15258/) (2025)
- [DictPFL: Efficient and Private Federated Learning on Encrypted Gradients](https://mlsanity.com/paper/2510.21086/) (2025)
- [CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption](https://mlsanity.com/paper/2602.01621/) (2026)
- [FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHE](https://mlsanity.com/paper/2511.22434/) (2025)
- [RobPI: Robust Private Inference against Malicious Client](https://mlsanity.com/paper/2602.19918/) (2026)
- [CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning](https://mlsanity.com/paper/2606.08027/) (2026)
- [FEnc2: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encoding](https://mlsanity.com/paper/2606.16359/) (2026)
- [Repurposing CLIP to Localize at Pixel Level](https://mlsanity.com/paper/2607.05253/) (2026)

## Abstract (arXiv)

Recently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption. Prior PPNNs adopt mobile network architectures such as SqueezeNet for smaller computing overhead, but we find na"ively using mobile network architectures for a PPNN does not necessarily achieve shorter inference latency. Despite having less parameters, a mobile network architecture typically introduces more layers and increases the HE multiplicative depth of a PPNN, thereby prolonging its inference latency. In this paper, we propose a HE-friendly privacy-preserving Mobile neural nETwork architecture, HEMET. Experimental results show that, compared to state-of-the-art (SOTA) PPNNs, HEMET reduces the inference latency by 59.3%~ 61.2%, and improves the inference accuracy by 0.4 % ~ 0.5%.