SetPrint: Black-Box LLM Fingerprinting via Setwise Correspondence of Response Changes
中文摘要
SetPrint通过分析查询扰动引起的响应变化集合对应关系,实现黑盒LLM指纹识别,从而判断目标模型是否衍生自源模型。
English Summary
SetPrint is a black-box fingerprinting method that identifies if a target LLM derives from a source model by analyzing setwise correspondences in response changes from perturbed queries.
arXiv:2611.12950v1 Announce Type: new Abstract: Black-box LLM fingerprinting aims to determine whether a target model was derived from a source model when only the output responses to input queries are observable. One way to reveal this relationship is to perturb each query and observe the resulting responses of both models, yielding two corresponding sets of response variations. These sets provide two complementary sources of information: the relations among response changes within each set, and the correspondence of response changes between the two sets. Existing approaches, however, have not fully exploited both. We introduce \textbf{SetPrint}, a training-free method that jointly captures both within-set relations and between-set correspondence. SetPrint expresses each response change relative to the mean change of its own set, and then compares changes from the two models that were induced by the same perturbation. On LeaFBench, SetPrint consistently outperforms existing training-free black-box fingerprinting methods. Further analyses attribute these gains to both within-set relations and between-set correspondence.