DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909996356206592 |
|---|---|
| author | Xu, Zhenhua Zhao, Yiran Zhong, Mengting Kong, Dezhang Lin, Changting Qiao, Tong Han, Meng |
| author_facet | Xu, Zhenhua Zhao, Yiran Zhong, Mengting Kong, Dezhang Lin, Changting Qiao, Tong Han, Meng |
| contents | The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either rely on rare tokens -- leading to high-perplexity inputs susceptible to filtering -- or use fixed trigger-response mappings that are brittle to leakage and post-hoc adaptation. We propose \textsc{Dual-Layer Nested Fingerprinting} (DNF), a black-box method that embeds a hierarchical backdoor by coupling domain-specific stylistic cues with implicit semantic triggers. Across Mistral-7B, LLaMA-3-8B-Instruct, and Falcon3-7B-Instruct, DNF achieves perfect fingerprint activation while preserving downstream utility. Compared with existing methods, it uses lower-perplexity triggers, remains undetectable under fingerprint detection attacks, and is relatively robust to incremental fine-tuning and model merging. These results position DNF as a practical, stealthy, and resilient solution for LLM ownership verification and intellectual property protection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08223 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection Xu, Zhenhua Zhao, Yiran Zhong, Mengting Kong, Dezhang Lin, Changting Qiao, Tong Han, Meng Cryptography and Security Artificial Intelligence The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either rely on rare tokens -- leading to high-perplexity inputs susceptible to filtering -- or use fixed trigger-response mappings that are brittle to leakage and post-hoc adaptation. We propose \textsc{Dual-Layer Nested Fingerprinting} (DNF), a black-box method that embeds a hierarchical backdoor by coupling domain-specific stylistic cues with implicit semantic triggers. Across Mistral-7B, LLaMA-3-8B-Instruct, and Falcon3-7B-Instruct, DNF achieves perfect fingerprint activation while preserving downstream utility. Compared with existing methods, it uses lower-perplexity triggers, remains undetectable under fingerprint detection attacks, and is relatively robust to incremental fine-tuning and model merging. These results position DNF as a practical, stealthy, and resilient solution for LLM ownership verification and intellectual property protection. |
| title | DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2601.08223 |