arXiv subjects

Hyeri Roh

Publications and source records attributed to Hyeri Roh.

5 recordsLinked to original sources

arXiv2026

Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic

Hybrid HE/2PC private CNN inference remains bottlenecked by prime-modulus homomorphic arithmetic in convolution and by a precision flow that runs ReLU at doubled bitwidth before invoking a separate truncation protocol. We present Jaguar, a system built on a single design choice--a power-of-two ciphertext ring--that addresses both. The choice enables SPA-Conv, a coefficient-domain convolution kernel that replaces NTT-centric polynomial multiplication with scalar-polynomial accumulation, and an exact ciphertext-side truncation by local right shifts that lets ReLU run directly at the target fixed-point precision and eliminates the post-ReLU truncation protocol. Where NTT remains genuinely useful--at the client, for the single polynomial multiplication during decryption--we recover it through an auxiliary NTT prime, preserving the power-of-two protocol substrate while keeping decryption O(N log N). On ImageNet-scale ResNet-18, ResNet-50, and MobileNetV2 with AVX disabled, Jaguar achieves 2.07-3.72x lower end-to-end latency than Cheetah and 2.16-3.36x lower than Rhombus, with 1.16-1.76x lower communication than Cheetah.

cs.CR↗

arXiv2024

Flash: A Hybrid Private Inference Protocol for Deep CNNs with High Accuracy and Low Latency on CPU

This paper presents Flash, an optimized private inference (PI) hybrid protocol utilizing both homomorphic encryption (HE) and secure two-party computation (2PC), which can reduce the end-to-end PI latency for deep CNN models less than 1 minute with CPU. To this end, first, Flash proposes a low-latency convolution algorithm built upon a fast slot rotation operation and a novel data encoding scheme, which results in 4-94x performance gain over the state-of-the-art. Second, to minimize the communication cost introduced by the standard nonlinear activation function ReLU, Flash replaces the entire ReLUs with the polynomial $x^2+x$ and trains deep CNN models with the new training strategy. The trained models improve the inference accuracy for CIFAR-10/100 and TinyImageNet by 16% on average (up to 40% for ResNet-32) compared to prior art. Last, Flash proposes an efficient 2PC-based $x^2+x$ evaluation protocol that does not require any offline communication and that reduces the total communication cost to process the activation layer by 84-196x over the state-of-the-art. As a result, the end-to-end PI latency of Flash implemented on CPU is 0.02 minute for CIFAR-100 and 0.57 minute for TinyImageNet classification, while the total data communication is 0.07GB for CIFAR-100 and 0.22GB for TinyImageNet. Flash improves the state-of-the-art PI by 16-45x in latency and 84-196x in communication cost. Moreover, even for ImageNet, Flash can deliver the latency less than 1 minute on CPU with the total communication less than 1GB.

cs.CR↗

arXiv2023

Hyena: Optimizing Homomorphically Encrypted Convolution for Private CNN Inference

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.

cs.CR↗

arXiv2023

NeuralEQ: Neural-Network-Based Equalizer for High-Speed Wireline Communication

With the growing demand for high-bandwidth applications like video streaming and cloud services, the data transfer rates required for wireline communication keeps increasing, making the channel loss a major obstacle in achieving low bit error rate (BER). Equalization techniques such as feed-forward equalizer (FFE) and decision feedback equalizer (DFE) are commonly used to compensate for channel loss in wireline communication, but they have limitations in terms of noise boosting and timing constraints. On the other hand, the forward-backward algorithm can achieve better BER performance, but its high complexity makes it impractical for wireline communication. In this work, we propose a novel neural network, NeuralEQ, that effectively mimics the forward-backward algorithm and performs better than FFE and DFE while reducing complexity of the forward-backward algorithm. Performance of NeuralEQ is verified through simulations using real channels.

eess.SP↗

arXiv2023

A Context-Aware Readout System for Sparse Touch Sensing Array Using Ultra-low-power Always-on Event Detection

Increasing demand for larger touch screen panels (TSPs) places more energy burden to mobile systems with conventional sensing methods. To mitigate this problem, taking advantage of the touch event sparsity, this paper proposes a novel TSP readout system that can obtain huge energy saving by turning off the readout circuits when none of the sensors are activated. To this end, a novel ultra-low-power always-on event and region of interest detection based on lightweight compressed sensing is proposed. Exploiting the proposed event detector, the context-aware TSP readout system, which can improve the energy efficiency by up to 42x, is presented.

eess.SP↗