ZK-SR117：面向聚合公平借贷指标的分块零知识证明设计，及指向完整SR 11-7覆盖的控制映射

中文摘要 AI 辅助

在受监管决策场景（信用审批、欺诈检测、贷款批准）中部署机器学习模型，需向审计人员证明模型的公平性与鲁棒性，同时不暴露模型权重或客户数据。本文针对美国银行监管机构发布的SR 11-7与OCC 2011-12指引下的该证明问题展开研究，提出一种分块零知识电路设计，用于对承诺的、随机数采样的2022年HMDA住房抵押贷款真实数据批次，证明聚合公平性统计量——人口均等差距（demographic-parity gap）。该设计端到端验证：处理32768行数据，生成32份独立验证的zkSNARK证明，聚合证明的差距与真实保留值偏差为0.0029，每块证明耗时不足4秒。我们还通过在相同架构上证明第二项控制项（10个分箱下的预期校准误差ECE）展示了扩展性，所有32块均通过验证，每块证明耗时约14.7秒，在相同承诺数据上，证明的ECE与明文值偏差为0.00037。我们将该设计与两种替代方案对比：一是直接求和电路，其在处理数千行数据时会溢出；二是树化简电路，数值精确但编译难度极大，结果显示分块设计是唯一达到该规模的方案。我们还发现并定位了真实的数据质量故障（一个哨兵代码异常值扭曲了电路证明及公平性统计量本身），并通过已发布的预处理规范解决了该问题。此外，我们提出了SR 11-7与OCC 2011-12控制语言到零知识陈述的更完整映射（9项控制要素，涵盖可靠性、校准、鲁棒性与漂移）、一种抗银行端择优选择的随机数采样协议，以及部署用威胁模型，该部分为设计工作而非已实现结果。我们端到端验证了2项控制项、1类模型、1项任务，其余内容已划定范围并留待未来工作。

英文摘要

Deploying ML models in regulated decision-making (credit underwriting, fraud detection, loan approval) requires demonstrating fairness and robustness to auditors without exposing model weights or customer data. We address this attestation problem for U.S. bank supervision under SR 11-7 and OCC 2011-12 guidance. We present a chunked zero-knowledge circuit design that attests an aggregated fairness statistic - the demographic-parity gap - on committed, nonce-sampled batches of real 2022 HMDA mortgage data, and demonstrate it end-to-end: 32,768 rows, 32 independently verified zkSNARK proofs, aggregated attested gap within 0.0029 of the true held-out value, per-chunk proving under 4 seconds. We also demonstrate extensibility by attesting a second control on the identical architecture - expected calibration error at 10 bins - with all 32 chunks verified, per-chunk proving at about 14.7 seconds, and attested ECE within 0.00037 of the plaintext value on the same committed rows. We compare this design against two alternatives - a flat summation circuit, which overflows past a few thousand rows, and a tree-reduction circuit, numerically exact but intractable to compile - and find the chunked design is the only one that reached this scale. We discovered and root-caused a genuine data-quality failure (a sentinel-code outlier distorting circuit proving and the fairness statistic itself) and resolved it with a published preprocessing specification. We also propose a fuller mapping from SR 11-7 and OCC 2011-12 control language to zero-knowledge statements (nine control elements spanning soundness, calibration, robustness, and drift), a nonce-based sampling protocol resisting bank-side cherry-picking, and a threat model for deployment, proposed as design work, not implemented results. Two controls, one model class, one task are demonstrated end-to-end; the rest is scoped and left as future work.

发表机构

• Westcliff University（韦斯特克利夫大学）
• Northern University Bangladesh（孟加拉国北方大学）
• Washington University of Science and Technology（华盛顿科技大学）
• Stanton University（斯坦顿大学）

机构由 AI 辅助整理，请以论文原文为准。