提出可证明的模型溯源集合，确保溯源结果可靠且可控。
Provable Model Provenance Set for Large Language Models
- 通过序贯测试排除法构建可信溯源集
- 在指定置信度下覆盖全部真实来源
- 适合模型版权审计与责任追溯场景
大规模语言模型的未经授权使用和归属错误问题日益严重，亟需可靠的模型溯源分析。现有方法多依赖启发式指纹匹配规则，缺乏可证明的误差控制，常忽略多源情况，导致溯源结论不可靠。本文首次形式化模型溯源问题并提供可证明的保障，要求在指定置信水平下严格覆盖所有真实来源。提出模型溯源集（MPS），采用序贯测试与排除策略，自适应构建满足保证的小型候选集。核心思想是在候选池中逐项检验溯源存在的显著性，从而在用户指定置信度下建立渐近可证明的保障。大量实验表明，MPS能有效实现目标溯源覆盖率，同时严格限制无关模型的误纳入，并展现出在归属确认与审计任务中的实际潜力。
原文摘要 · Abstract (English)
The growing prevalence of unauthorized model usage and misattribution has increased the need for reliable model provenance analysis. However, existing methods largely rely on heuristic fingerprint-matching rules that lack provable error control and often overlook the existence of multiple sources, leaving the reliability of their provenance claims unverified. In this work, we first formalize the model provenance problem with provable guarantees, requiring rigorous coverage of all true provenances at a prescribed confidence level. Then, we propose the Model Provenance Set (MPS), which employs a sequential test-and-exclusion procedure to adaptively construct a small set satisfying the guarantee. The key idea of MPS is to test the significance of provenance existence within a candidate pool, thereby establishing a provable asymptotic guarantee at a user-specific confidence level. Extensive experiments demonstrate that MPS effectively achieves target provenance coverage while strictly limiting the inclusion of unrelated models, and further reveal its potential for practical provenance analysis in attribution and auditing tasks.
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。