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.

翻译：混合HE/2PC私有CNN推理的瓶颈依然在于卷积中基于素数模数的同态算术，以及一个精度流——该流要求以加倍位宽运行ReLU后，再调用独立的截断协议。我们提出Jaguar系统，其核心设计选择——采用2的幂次密文环——同时解决了这两个问题。该选择实现了SPA-Conv，一种系数域卷积内核，用标量-多项式累加取代了以NTT为中心的多项式乘法，以及一种通过局部右移实现的精确密文端截断技术，使ReLU能直接以目标定点精度运行，从而消除了ReLU后的截断协议。当NTT在实际场景中确实有效时（即在客户端，用于解密过程中的单次多项式乘法），我们通过辅助NTT素数恢复其功能，在保持2的幂次协议基底的同时，将解密复杂度维持在O(N log N)。在禁用AVX的ImageNet规模ResNet-18、ResNet-50及MobileNetV2上，Jaguar相比Cheetah和Rhombus分别实现了2.07-3.72倍和2.16-3.36倍的端到端延迟降低，同时相比Cheetah通信量减少1.16-1.76倍。