让深度卷积网络在同态加密下高效推理，支持任意分辨率图像
Peregrine: One-Shot Fine-Tuning for FHE Inference of General Deep CNNs
- 用单阶段微调将预训练模型转为低次多项式形式，保持精度
- 实现跨架构的端到端同态加密推理，支持高分辨率图像处理
- 首次在目标检测中实现基于低次多项式的同态加密推理
我们解决通用深度卷积神经网络在同态加密（FHE）推理中的两大挑战：如何用低次多项式近似ReLU等非线性激活函数以最小化精度损失，以及克服密文容量限制对高分辨率图像处理的制约。贡献有二：(1) 提出单阶段微调（SFT）策略，直接将预训练CNN转换为适合FHE的形式，仅需极少训练开销即可获得竞争力的精度；(2) 设计通用交错打包（GIP）方案，兼容任意空间分辨率的特征图，并配备一系列精心设计的同态运算符，确保计算全程保持GIP加密形式。该方法实现跨多种CNN架构的高效端到端FHE推理。在CIFAR-10、ImageNet和MS COCO上的实验表明，通过SFT获得的FHE友好模型精度与使用ReLU或SiLU激活函数的基线相当。此外，本工作首次展示了基于低次多项式激活的YOLO架构在目标检测中的同态加密推理。
原文摘要 · Abstract (English)
We address two fundamental challenges in adapting general deep CNNs for FHE-based inference: approximating non-linear activations such as ReLU with low-degree polynomials while minimizing accuracy degradation, and overcoming the ciphertext capacity barrier that constrains high-resolution image processing on FHE inference. Our contributions are twofold: (1) a single-stage fine-tuning (SFT) strategy that directly converts pre-trained CNNs into FHE-friendly forms using low-degree polynomials, achieving competitive accuracy with minimal training overhead; and (2) a generalized interleaved packing (GIP) scheme that is compatible with feature maps of virtually arbitrary spatial resolutions, accompanied by a suite of carefully designed homomorphic operators that preserve the GIP-form encryption throughout computation. These advances enable efficient, end-to-end FHE inference across diverse CNN architectures. Experiments on CIFAR-10, ImageNet, and MS COCO demonstrate that the FHE-friendly CNNs obtained via our SFT strategy achieve accuracy comparable to baselines using ReLU or SiLU activations. Moreover, this work presents the first demonstration of FHE-based inference for YOLO architectures in object detection leveraging low-degree polynomial activations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。