# ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition

arXiv: https://arxiv.org/abs/2003.05328 · HTML: https://mlsanity.com/paper/2003.05328/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [A Study of Face Obfuscation in ImageNet](https://mlsanity.com/paper/2103.06191/) (2021)
- [A Review on Visual Privacy Preservation Techniques for Active and Assisted Living](https://mlsanity.com/paper/2112.09422/) (2021)
- [Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial Examples](https://mlsanity.com/paper/2310.12707/) (2023)
- [Privacy-Preserving Semantic Segmentation from Ultra-Low-Resolution RGB Inputs](https://mlsanity.com/paper/2507.16034/) (2025)

## Abstract (arXiv)

In this work, we propose ENSEI, a secure inference (SI) framework based on the frequency-domain secure convolution (FDSC) protocol for the efficient execution of privacy-preserving visual recognition. Our observation is that, under the combination of homomorphic encryption and secret sharing, homomorphic convolution can be obliviously carried out in the frequency domain, significantly simplifying the related computations. We provide protocol designs and parameter derivations for number-theoretic transform (NTT) based FDSC. In the experiment, we thoroughly study the accuracy-efficiency trade-offs between time- and frequency-domain homomorphic convolution. With ENSEI, compared to the best known works, we achieve 5--11x online time reduction, up to 33x setup time reduction, and up to 10x reduction in the overall inference time. A further 33% of bandwidth reductions can be obtained on binary neural networks with only 1% of accuracy degradation on the CIFAR-10 dataset.