SetPrint: Black-Box Fingerprinting Method Identifies LLMs via Setwise Response Changes
A new arXiv paper introduces SetPrint, a black-box LLM fingerprinting technique that determines whether a target model was derived from a source model using setwise correspondence of response changes to input queries.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-11 05:00 · arXiv cs.AI
SetPrint: Black-Box LLM Fingerprinting via Setwise Correspondence of Response Changes