UniHENN: Designing More Versatile Homomorphic Encryption-based CNNs without im2col

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