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. \textsc{AttnDiff} probes minimally edited prompt pairs that induce controlled semantic conflicts, captures differential attention patterns, summarizes them with compact spectral descriptors, and compares models using CKA. Across Llama-2/3 and Qwen2.5 (3B--14B) and additional open-source families, it yields high similarity for related derivatives while separating unrelated model families (e.g., >0.98 vs.\ <0.22 with M=60 probes). With 5--60 multi-domain probes, it supports practical provenance verification and accountability.
@article{arxiv.2604.05502,
title = {AttnDiff: Attention-based Differential Fingerprinting for Large Language Models},
author = {Haobo Zhang and Zhenhua Xu and Junxian Li and Shangfeng Sheng and Dezhang Kong and Meng Han},
journal= {arXiv preprint arXiv:2604.05502},
year = {2026}
}