提出GKR-HND协议，让第三方推理更可信且高效。
Agree on the Model, Verify the Inference: GKR Protocols for HND-Based Transformer Inference
- 用GKR证明框架验证HND模型的多项式主干计算
- 实测证明无需密集矩阵重演也能正确验证推理路径
- 适合需要安全外包推理的场景，如云AI服务
外包Transformer推理存在模型替换和执行不完整风险，而直接重演又丧失了委托计算的优势。本文提出GKR-HND协议，用于验证基于同态-非同态分解（HND）的Transformer模型。保留验证者检查GKR证明记录和注册权重开放值，但将昂贵的公开计算任务委派给指定计算工作者。在验证者诚实且证明者-工作者不共谋的前提下，只有当工作者签名的、请求绑定的响应与证明声明一致时，验证者才接受。使用预训练HND模型的实验验证了证明路径的正确性及无需密集矩阵重演即可完成委派计算。
原文摘要 · Abstract (English)
Outsourced Transformer inference exposes clients to model substitution and incomplete execution, while direct replay removes the computational benefit of delegation. We present GKR-HND, a registered-model protocol for verifying the polynomial backbone of Homomorphic--Nonhomomorphic Decomposition Transformers. The retained verifier checks the GKR transcript and registered-weight openings, but delegates expensive public evaluations to an assigned computation worker. Assuming an honest retained verifier and prover--worker non-collusion, the verifier accepts only when the worker's signed, request-bound response agrees with the proof claims. Experiments with pretrained HND models validate the proof path and the delegated public computation without dense-matrix replay.
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。