# Efficient Pruning for Machine Learning Under Homomorphic Encryption

arXiv: https://arxiv.org/abs/2207.03384 · HTML: https://mlsanity.com/paper/2207.03384/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 7 Jul 2022.

## Builds on (most cited first, 15 of 15)

- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [XONN: XNOR-based Oblivious Deep Neural Network Inference](https://mlsanity.com/paper/1902.07342/) (2019)
- [Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference](https://mlsanity.com/paper/1811.09953/) (2018)
- [Membership Inference Attacks and Defenses in Neural Network Pruning](https://mlsanity.com/paper/2202.03335/) (2022)
- [COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest CT Images](https://mlsanity.com/paper/2009.05383/) (2020)
- [HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture](https://mlsanity.com/paper/2106.00038/) (2021)
- [HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data](https://mlsanity.com/paper/2011.01805/) (2020)
- [nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data](https://mlsanity.com/paper/1908.04172/) (2019)
- [A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework](https://mlsanity.com/paper/2003.06513/) (2020)
- [A methodology for training homomorphicencryption friendly neural networks](https://mlsanity.com/paper/2111.03362/) (2021)
- [Popcorn: Paillier Meets Compression For Efficient Oblivious Neural Network Inference](https://mlsanity.com/paper/2107.01786/) (2021)

## Built on by (most cited first, 2 of 2)

- [PrivCirNet: Efficient Private Inference via Block Circulant Transformation](https://mlsanity.com/paper/2405.14569/) (2024)
- [PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption](https://mlsanity.com/paper/2607.18342/) (2026)

## Abstract (arXiv)

Privacy-preserving machine learning (PPML) solutions are gaining widespread popularity. Among these, many rely on homomorphic encryption (HE) that offers confidentiality of the model and the data, but at the cost of large latency and memory requirements. Pruning neural network (NN) parameters improves latency and memory in plaintext ML but has little impact if directly applied to HE-based PPML. We introduce a framework called HE-PEx that comprises new pruning methods, on top of a packing technique called tile tensors, for reducing the latency and memory of PPML inference. HE-PEx uses permutations to prune additional ciphertexts, and expansion to recover inference loss. We demonstrate the effectiveness of our methods for pruning fully-connected and convolutional layers in NNs on PPML tasks, namely, image compression, denoising, and classification, with autoencoders, multilayer perceptrons (MLPs) and convolutional neural networks (CNNs). We implement and deploy our networks atop a framework called HElayers, which shows a 10-35% improvement in inference speed and a 17-35% decrease in memory requirement over the unpruned network, corresponding to 33-65% fewer ciphertexts, within a 2.5% degradation in inference accuracy over the unpruned network. Compared to the state-of-the-art pruning technique for PPML, our techniques generate networks with 70% fewer ciphertexts, on average, for the same degradation limit.