Batch Inference on Deep Convolutional Neural Networks With Fully Homomorphic Encryption Using Channel-By-Channel Convolutions

JH Cheon, M Kang, T Kim, J Jung… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Secure Machine Learning as a Service (MLaaS) is a viable solution where clients seek
secure ML computation delegation while protecting sensitive data. We propose an efficient …

DCT-CryptoNets: Scaling private inference in the frequency domain

A Roy, K Roy - arXiv preprint arXiv:2408.15231, 2024 - arxiv.org
The convergence of fully homomorphic encryption (FHE) and machine learning offers
unprecedented opportunities for private inference of sensitive data. FHE enables …

Homomorphic WiSARDs: Efficient Weightless Neural Network training over encrypted data

L Neumann, A Guimarães, DF Aranha… - arXiv preprint arXiv …, 2024 - arxiv.org
The widespread application of machine learning algorithms is a matter of increasing
concern for the data privacy research community, and many have sought to develop privacy …

Privacy-preserving Network Anomaly Detection on Homomorphically Encrypted Data

T Wingarz, A See, F Gondesen… - 2024 IEEE Conference …, 2024 - ieeexplore.ieee.org
With the increasing reliance on cloud computing for managed security services, sensitive
data, such as network or host data, is increasingly not processed on-premise anymore. To …

Privacy Preserving Genomic Data Imputation using Autoencoders

M Pratapa, A Essex - Procedia Computer Science, 2024 - Elsevier
Next-generation sequencing technologies have significantly increased the availability of
genomic databases. These databases can be used for numerous applications in genome …

Homomorphic Encryption for Privacy Preservation in Occupancy Sensor-Based Smart Lighting

AG Putrada, M Abdurohman… - … Conference on Data …, 2024 - ieeexplore.ieee.org
Occupancy sensor-based smart lighting is very practical because the light status can change
automatically according to human activity under the lighting area. However, on the other …

[引用][C] 근사동형기반의암호화된부동소수점표현

신재원, 박지혜, 신호준, 이윤호 - 한국정보과학회학술발표논문집, 2023 - dbpia.co.kr
요 약본 연구는 완전 동형 암호에서의 부동소수점 표현 방식을 제안하고 실용적인 사칙 연산과
비교 연산을제안, 구현했다. CKKS (Cheon-Kim-Kim-Song) 는 암호문 간의 실수의 연산을 …