3 papers
cs.CR2026
Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic
Yewon Jeong, Nayoung Jung, Hyeri Roh +1
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 in…
cs.CR2025
Hyena: Optimizing Homomorphically Encrypted Convolution for Private CNN Inference
Hyeri Roh, Woo-Seok Choi
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 whe…
cs.CR2025
Flash: A Hybrid Private Inference Protocol for Deep CNNs with High Accuracy and Low Latency on CPU
Hyeri Roh, Jinsu Yeo, Yeongil Ko +3
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 t…