让加密计算与推理模型协同设计，解决云端隐私难题
Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference
- 将加密方案与推理结构互相适配，降低计算开销
- 通过架构约束减少同态加密的核心成本
- 适合关注隐私计算与高效部署的研究者
现代云推理存在双向隐私风险：用户需向服务方暴露敏感输入，而服务方必须在可能泄露的环境中执行专有模型权重。全同态加密（FHE）虽能提供密码学保障，但对现代架构而言仍过于昂贵。我们主张通过协同设计来推动进展：一方面针对推理电路的静态结构定制FHE方案与编译器，另一方面限制推理架构以减少同态计算的主要成本来源。本文提出‘中间会合’范式，并明确了两个方向的具体优化目标。
原文摘要 · Abstract (English)
Modern cloud inference creates a two sided privacy problem where users reveal sensitive inputs to providers, while providers must execute proprietary model weights inside potentially leaky execution environments. Fully homomorphic encryption (FHE) offers cryptographic guarantees but remains prohibitively expensive for modern architectures. We argue that progress requires co-design where specializing FHE schemes/compilers for the static structure of inference circuits, while simultaneously constraining inference architectures to reduce dominant homomorphic cost drivers. We outline a meet in the middle agenda and concrete optimization targets on both axes.
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。