arXiv cs.AI· Zexun Wang·· 2 天前AI 评分18
Matoi：面向智能体授权的后果证据选择性重验证机制
Matoi: Selective Revalidation of Consequence Evidence for Agent Authorization
AI 导读
Matoi 将可复用的后果证据与当前执行权限、持久发生历史分离，用有限查询感知契约覆盖分支、有序集合与否定查询。在 1,440 单元匹配线研究中，输入字节相同时复用使 JS 完整生命周期成本降低 3.49%、Python 降低 1.79%；AgentDojo Banking 映射覆盖 5/16 用户计划与 7/9 攻击计划，两种治理策略均保留 5 笔正常转账并拒绝 35 次复用攻击计划/策略交叉。
正文 · 原文
Abstract:Matoi separates reusable consequence evidence from current execution authority and durable occurrence history. Its finite query-aware contract covers branches, ordered collections and negative lookups. A consumer reuses only its own checked evidence whose observations remain valid; signed requests, live grants, quota and uncertain outcomes remain separate obligations. Conditional correctness arguments distinguish locally serialized claims from nontransactional remote effects. Two studies strengthen cost attribution and domain evaluation. A 1,440-cell matched-wire study repeats 144 authored inputs. With compact input bytes identical, reuse reduces complete lifecycle cost by 3.49 percent in JS and 1.79 percent in Python. Combined representation/reuse reductions against full proof are 10.87 and 16.53 percent; five of twelve family intervals for the matched comparison cross one in each language. A prospectively frozen AgentDojo Banking mapping covers 5/16 user plans and 7/9 attack plans. Both governed strategies preserve five exact benign transfers and refuse 35 reused attack-plan/policy crosses. Pre-satisfied utility predicates are reported separately from completed work. These are original scripted synthetic tools, not autonomous agents or a real bank. Earlier studies retain cheaper protected-cache alternatives, policy-compatible phishing, provider duplication and post-claim revocation. Separate JS/Python consumers establish finite-profile interoperability within the same project; durable recovery rechecks evidence and retains uncertain reservations. The results support a bounded, auditable reuse and execution contract, not a new general incremental algorithm, arbitrary-tool closure, atomic third-party commitment or production superiority.
| Comments: | 55 pages, 4 figures. Includes an 18-page technical manuscript and a 33-page detailed supplement as ancillary files. Research preprint; not peer reviewed |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.21394 [cs.CR] |
| (or arXiv:2610.21394v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21394 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zexun Wang [view email]
[v1]
Thu, 15 Oct 2026 07:13:17 UTC (735 KB)
来源：arXiv cs.AI · arxiv.org