AI 中文总结
本研究提出将IETF RATS架构与行动证据包组合，实现AI智能体的硬件根证明，通过仿真TPM实验验证了该方案的可行性。
AI 中文摘要
行动证据包（AEP）是一种已签名、仅追加的记录，记录了AI智能体的行为、授权该行为的主体或对象以及行为结果，它是软件层产物，向验证者呈现智能体运行时报告的自身行为故事。本文指出，此类软件证明是必要的，但不够充分：当验证者的问题从“智能体声称它做了什么？”转变为“操作者声称部署的特定模型版本是否在未修改的硬件上实际产生了该输出？”时，仅靠AEP无法回答，缺失的要素是硬件信任根——证明平台的 measured boot 和运行时状态与认可的参考匹配。IETF远程证明程序（RATS）架构（RFC 9334）和开源RATS验证器实现Veraison（来自机密计算联盟/ Linux基金会）恰好提供了这一要素。我们提出组合证明：根据RATS评估的硬件证据与软件AEP绑定。我们将小型验证器词汇（授权/未授权/不确定/已证明/有争议/已过期）映射到RATS评估结果，并通过小型执行实验证明可行性：在软件可信平台模块（TPM；swtpm模拟器）上，输出绑定协议将AEP结果的哈希与新的评估器随机数折叠为证明密钥签名的quote，其中模型工件测量值存储在平台寄存器中。最小化RATS验证器替身按设计解析三种平台结果：良好新鲜quote为已证明，模型测量值被替换为有争议，陈旧quote重放为已过期，且拒绝绑定到有效quote的伪造AEP结果。该结果是仿真硬件上的可行性演示，而非硬件根保证。
英文摘要
An action evidence package (AEP) is a signed, append-only record of what an AI agent did, who or what authorised the action, and what the outcome was. It is a software-layer artefact: it tells a verifier the story of an action as the agent's own runtime reports it. This note argues that software attestation of this kind is necessary but not sufficient. When a verifier's question shifts from "what does the agent claim it did?" to "did the specific model version the operator claims to have deployed actually produce this output, on unmodified hardware?", the AEP alone cannot answer. The missing element is a hardware root of trust: an attestation that the measured boot and runtime state of the platform match an endorsed reference. The IETF Remote Attestation Procedures (RATS) architecture (RFC 9334) and Veraison, an open-source RATS Verifier implementation (Confidential Computing Consortium / Linux Foundation), supply exactly this. We propose a composite attestation: hardware Evidence appraised under RATS, bound to a software AEP. We map a small verifier vocabulary (Authorised / Unauthorised / Indeterminate / Attested / Contested / Expired) onto RATS appraisal outcomes, and demonstrate feasibility with a small executed experiment: on a software Trusted Platform Module (TPM; the swtpm emulator), an output-binding protocol folds the hash of an AEP outcome and a fresh appraiser nonce into an attestation-key-signed quote, with a model-artefact measurement carried in a platform register. A minimal RATS-Verifier stand-in resolves the three platform outcomes as designed -- Attested for a good, fresh quote; Contested when the model measurement is swapped; Expired when a stale quote is replayed -- and rejects a forged AEP outcome bound to a valid quote. The result is a feasibility demonstration on emulated hardware, not a hardware-rooted guarantee.
Comments9 pages, 1 figure, 1 table. Technical note. Also deposited at Zenodo: doi:10.5281/zenodo.20818671
