Feb. 6, 2024, 5:10 a.m. | Hyunmin Choi Jihun Kim Seungho Kim Seonhye Park Jeongyong Park Wonbin Choi Hyoungshick Kim

cs.CR updates on arXiv.org arxiv.org

Homomorphic encryption enables computations on encrypted data without decryption, which is crucial for privacy-preserving cloud services. However, deploying convolutional neural networks (CNNs) with homomorphic encryption encounters significant challenges, particularly in converting input data into a two-dimensional matrix for convolution, typically achieved using the im2col technique. While efficient, this method limits the variety of deployable CNN models due to compatibility constraints with the encrypted data structure. UniHENN, a homomorphic encryption-based CNN architecture, eliminates the need for im2col, ensuring compatibility with a …

challenges cloud cloud services cnns convolutional neural networks cs.cr data decryption encrypted encrypted data encryption homomorphic encryption input matrix networks neural networks privacy services

Information Technology Specialist I, LACERA: Information Security Engineer

@ Los Angeles County Employees Retirement Association (LACERA) | Pasadena, CA

Consultant, SOC 2 | Remote US

@ Coalfire | United States

Senior Consultant, PCI QSA | Remote US

@ Coalfire | United States

Cyber Forensics Unit Assurance Lead

@ Financial Conduct Authority | London

Field Service Engineer

@ ManTech | 765P - Bldg 90135MohawkDr,Killeen,TX

Field Service Technician (UAE Expatriate Assignment)

@ Motorola Solutions | Texas, US Offsite