AI RESEARCH

AttnDiff: Attention-based Differential Fingerprinting for Large Language Models

arXiv CS.LG

ArXi:2604.05502v1 Announce Type: cross Protecting the intellectual property of open-weight large language models (LLMs) requires verifying whether a suspect model is derived from a victim model despite common laundering operations such as fine-tuning (including PPO/DPO), pruning/compression, and model merging. We propose \textsc{AttnDiff}, a data-efficient white-box framework that extracts fingerprints from models via intrinsic information-routing behavior.