# Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks

arXiv: https://arxiv.org/abs/2604.16834 · HTML: https://mlsanity.com/paper/2604.16834/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 16 of 16)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [Low Latency Privacy Preserving Inference](https://mlsanity.com/paper/1812.10659/) (2018)
- [Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network](https://mlsanity.com/paper/2106.07229/) (2021)
- [Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference](https://mlsanity.com/paper/1811.09953/) (2018)
- [nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data](https://mlsanity.com/paper/1908.04172/) (2019)
- [AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE](https://mlsanity.com/paper/2310.08012/) (2023)
- [Orion: A Fully Homomorphic Encryption Framework for Deep Learning](https://mlsanity.com/paper/2311.03470/) (2023)
- [CryptoNN: Training Neural Networks over Encrypted Data](https://mlsanity.com/paper/1904.07303/) (2019)
- [Intel HEXL: Accelerating Homomorphic Encryption with Intel AVX512-IFMA52](https://mlsanity.com/paper/2103.16400/) (2021)
- [To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding](https://mlsanity.com/paper/2203.14646/) (2022)
- [TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecture](https://mlsanity.com/paper/2302.01584/) (2023)
- [Toward Practical Privacy-Preserving Convolutional Neural Networks Exploiting Fully Homomorphic Encryption](https://mlsanity.com/paper/2310.16530/) (2023)
- [Co-ML: Collaborative Machine Learning Model Building for Developing Dataset Design Practices](https://mlsanity.com/paper/2311.09088/) (2023)
- [Intelligent Cross-Organizational Process Mining: A Survey and New Perspectives](https://mlsanity.com/paper/2407.11280/) (2024)
- [FHEON: A Configurable Framework for Developing Privacy-Preserving Neural Networks Using Homomorphic Encryption](https://mlsanity.com/paper/2510.03996/) (2025)

## Abstract (arXiv)

Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphic Encryption (HE) enables computation directly on encrypted data, allowing neural network inference without revealing raw inputs. While prior works have largely focused on inference over a single encrypted image, batch processing of encrypted inputs lags behind, despite being critical for high-throughput inference scenarios and training-oriented workloads. In this work, we address this gap by developing optimized algorithms for batched HE-friendly neural networks. We also introduced a pipeline architecture designed to maximize resource efficiency for different batch size execution. We implemented these algorithms and evaluated our work using HE-friendly ResNet-20 and ResNet-34 models on encrypted CIFAR-10 and CIFAR-100 datasets, respectively. For ResNet-20, our approach achieves an amortized inference time of 8.86 seconds per image when processing a batch of 512 encrypted images, with a peak memory usage of 98.96 GB. These results represent a 1.78x runtime improvement and a 3.74x reduction in memory usage compared to the state-of-the-art design. For the deeper ResNet-34 model, we achieve an amortized inference time of 28.14 on a batch of 256 encrypted images using 246.78GB of RAM