arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.20504cs.CRcs.AI
收藏

中间相遇:一种用于全同态加密和AI推理的协同设计范式

Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference

University of Manchester(曼彻斯特大学);Sei Labs(Sei实验室);University of Portsmouth(普森特大学)

Bernardo Magri, Benjamin Marsh, Paul Gebheim

AI总结:

本文提出一种协同设计方法,通过优化FHE方案和推理架构,降低同态计算成本,解决云推理中的隐私问题。

摘要:

现代云推理创建了双方面的隐私问题,用户将敏感输入交给提供者,而提供者必须在可能泄露的执行环境中执行专有模型权重。全同态加密(FHE)提供加密保证,但对现代架构来说成本过高。我们主张通过协同设计来推进,即专门设计FHE方案/编译器以适应推理电路的静态结构,同时约束推理架构以减少主导的同态成本驱动因素。我们概述了一个中间相遇议程,并在两个轴上提出了具体的优化目标。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑