加密关键内容：选择性同态推理何时高效
Encrypt What Matters: When Selective Homomorphic Inference Is Efficient
浏览论文内容
中文总结 AI 辅助
本文研究选择性同态推理，仅加密敏感区域，发现局部性架构可大幅加速，全局混合架构无加速，局部性是关键属性。
中文摘要 AI 辅助
全同态加密（FHE）能够在私有数据上执行推理，而无需将其暴露给服务器，但在FHE下评估整个输入成本高昂。我们研究选择性同态推理，其中仅对敏感的兴趣区域（ROI）进行加密，而与该区域无关的计算则以明文形式执行。选择性评估在相同模型上产生与全FHE相同的输出，且无需重新训练。其效率取决于加密依赖关系在网络中传播的速度。对于较小的加密ROI，保持局部性的架构可实现数量级的同态评估加速，而具有早期全局混合的架构则基本无法获得加速。这些结果将局部性确定为控制选择性同态推理收益的关键架构属性。
英文摘要
Fully homomorphic encryption (FHE) enables inference on private data without revealing it to the server, but evaluating an entire input under FHE is expensive. We study \emph{selective homomorphic inference}, where only a sensitive region of interest (ROI) is encrypted, and computations independent of that region are performed in plaintext. Selective evaluation produces the same output as full FHE on the same model, without retraining. Its efficiency depends on how quickly encrypted dependencies spread through the network. For small encrypted ROIs, locality-preserving architectures can achieve order-of-magnitude homomorphic-evaluation speedups, whereas architectures with early global mixing provide essentially no speedup. These results identify locality as the key architectural property governing the benefit of selective homomorphic inference.
发表机构
- Massachusetts Institute of Technology（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。
