paper-with-me

Papers

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

2020-03-11 · CVPR 2020 6 · Song Bian, Tianchen Wang, Masayuki Hiromoto, Yiyu Shi, Takashi Sato

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.

📄 PDF Abstract BibTeX arXiv:2003.05328

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Falcon: Fast Spectral Inference on Encrypted Data

2020-12-01 · NeurIPS 2020 12 · Qian Lou, Wen-jie Lu, Cheng Hong, Lei Jiang

Homomorphic Encryption (HE) based secure Neural Networks(NNs) inference is one of the most promising security solutions to emerging Machine Learning as a Service (MLaaS). In the HE-based MLaaS setting, a client encrypts …

Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference

2025-10-08 · Kalyan Cheerla, Lotfi Ben Othmane, Kirill Morozov arxiv

Machine Learning (ML) is making its way into fields such as healthcare, finance, and Natural Language Processing (NLP), and concerns over data privacy and model confidentiality continue to grow. Privacy-preserving Machin…

Reverse Delegated Training and Private Inference via Perfectly-Secure Quantum Homomorphic Encryption

2026-02-13 · Sergio A. Ortega, Miguel A. Martin-Delgado arxiv

Quantum machine learning in cloud environments requires protecting sensitive data while enabling remote computation. Here we demonstrate the first realistic implementations of a perfectly-secure quantum homomorphic encry…

Quantum Machine Learning

BAYHENN: Combining Bayesian Deep Learning and Homomorphic Encryption for Secure DNN Inference

2019-06-03 · Peichen Xie, Bingzhe Wu, Guangyu Sun

Recently, deep learning as a service (DLaaS) has emerged as a promising way to facilitate the employment of deep neural networks (DNNs) for various purposes. However, using DLaaS also causes potential privacy leakage fro…

Privacy Preserving

TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation

2025-03-15 · Mayank Kumar, Jiaqi Xue, Mengxin Zheng, Qian Lou

Fully Homomorphic Encryption over the torus (TFHE) enables computation on encrypted data without decryption, making it a cornerstone of secure and confidential computing. Despite its potential in privacy preserving machi…

Code GenerationPrivacy PreservingRAGRetrieval-augmented Generation