🤖 AI Summary
In privacy-sensitive applications such as healthcare, homomorphic encryption (HE)-based private CNN inference suffers from prohibitively high latency in convolutional layers—accounting for over 85% of total inference time. To address this, this paper proposes an efficient HE convolution algorithm. Its core innovations include: (i) the first plaintext multiplication mechanism leveraging Walsh–Hadamard matrices, overcoming the inherent limitation of padding-based convolutions that preclude channel packing in outputs; and (ii) integration of adaptive HE parameter optimization with lazy modular reduction. Experiments on models including VGG-16 demonstrate up to 1.6–3.8× speedup in convolution computation, 2000–8000× compression in encrypted weight storage, 1.3–2.5× reduction in end-to-end inference latency, 2.1–7.9× lower memory footprint, and 1.4–1.5× decrease in communication overhead.
📝 Abstract
Private inference using homomorphic encryption has gained a great attention to leverage powerful predictive models, e.g., deep convolutional neural networks (CNNs), in the area where data privacy is crucial, such as in healthcare or medical services. Processing convolution layers, however, occupies a huge portion (more than 85%) of the total latency for private CNN inference. To solve this issue, this paper presents Hyena utilizing a novel homomorphic convolution algorithm that provides speedup, communication cost, and storage saving. We first note that padded convolution provides the advantage of model storage saving, but it does not support output channel packing, thereby increasing the amount of computation and communication. We address this limitation by proposing a novel plaintext multiplication algorithm using the Walsh-Hadamard matrix. Furthermore, we propose the optimization techniques to significantly reduce the latency of the proposed convolution by selecting the optimal encryption parameters and applying lazy reduction. Overall, Hyena achieves 1.6-3.8x speedup and reduces the weight storage by 2000-8000x compared to the conventional convolution. For deep CNNs like VGG-16, ResNet-20, and MobileNetV1 on ImageNet, Hyena reduces the end-to-end latency by 1.3-2.5x, the memory usage by 2.1-7.9x and communication cost by 1.4-1.5x compared to conventional method.