{"slug": "setprint-black-box-llm-fingerprinting-via-setwise-correspondence-of-response", "title": "SetPrint: Black-Box LLM Fingerprinting via Setwise Correspondence of Response Changes", "summary": "A new arXiv paper (2611.12950v1) introduces SetPrint, a training-free method for black-box LLM fingerprinting that determines whether a target model was derived from a source model using only observable output responses. SetPrint jointly captures relations among response changes within each model's set and the correspondence of changes between the two sets by expressing each response change relative to its own set's mean change, then comparing changes induced by the same perturbation. On LeaFBench, SetPrint consistently outperforms existing training-free black-box fingerprinting methods, with the authors attributing the gains to both within-set relations and between-set correspondence.", "body_md": "arXiv:2611.12950v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/setprint-black-box-llm-fingerprinting-via-setwise-correspondence-of-response", "canonical_source": "https://arxiv.org/abs/2611.12950", "published_at": "2026-11-11 05:00:00+00:00", "updated_at": "2026-11-11 05:22:57.170885+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-safety"], "entities": ["SetPrint", "LeaFBench", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/setprint-black-box-llm-fingerprinting-via-setwise-correspondence-of-response", "markdown": "https://wpnews.pro/news/setprint-black-box-llm-fingerprinting-via-setwise-correspondence-of-response.md", "text": "https://wpnews.pro/news/setprint-black-box-llm-fingerprinting-via-setwise-correspondence-of-response.txt", "jsonld": "https://wpnews.pro/news/setprint-black-box-llm-fingerprinting-via-setwise-correspondence-of-response.jsonld"}}