arXiv：cs.AI· Teruki Sano, Minoru Kuribayashi, Masao Sakai, Shuji Isobe, Eisuke Koizumi, Zhang Zhang, Satoru Matsumoto·· 4 小时前
概率性 AI 模型的 TP-CRIV 统计可分性刻画
Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models
AI 导读
研究刻画了概率性 AI 模型在第三方挑战-响应身份验证（TP-CRIV）中的统计可分性，将匹配与非匹配证明者的逐挑战行为与验证级可分性关联。该刻画明确了独立挑战数与重复响应数如何影响检测性能，可估算达到目标 AUC 所需的验证预算。作者用开放式挑战在 LLM 上实例化该刻画，实验显示匹配与非匹配可分离、理论与实测 AUC 高度吻合，且最小验证预算估计一致。
正文
Abstract:Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a claimant possesses a model identical to a remotely deployed model without directly accessing the reference model. However, for probabilistic AI models, repeated executions of the same query may produce different outputs and therefore different verification observations. This raises the question of how such stochastic evidence should be accumulated and how much evidence is required for reliable verification.
In this work, we characterize statistical separability in TP-CRIV of probabilistic AI models. Specifically, we relate challenge-wise behavior of matching and non-matching provers to verification-level separability. The characterization explicitly describes how the numbers of independent challenges and repeated responses affect detection performance and enables the verification budget required for a target AUC to be estimated. We instantiate the proposed characterization for LLMs using open-ended challenges. The experiments demonstrate matching-non-matching separation, close agreement between theoretical and empirical AUCs, and consistent estimates of the minimum verification budgets. These results provide a statistical basis for relating probabilistic model behavior to verification-level separability and the evidence required for third-party verification.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11163 [cs.CR] |
| (or arXiv:2610.11163v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11163 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Teruki Sano [view email]
[v1]
Thu, 8 Oct 2026 03:22:59 UTC (1,884 KB)
来源：arXiv：cs.AI · arxiv.org