Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.22692 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910005964308480 |
|---|---|
| author | Liu, Yiheng Ning, Junhao Xia, Sichen Sun, Haiyang Yang, Yang Chi, Hanyang Gao, Xiaohui Qiang, Ning Ge, Bao Han, Junwei Hu, Xintao |
| author_facet | Liu, Yiheng Ning, Junhao Xia, Sichen Sun, Haiyang Yang, Yang Chi, Hanyang Gao, Xiaohui Qiang, Ning Ge, Bao Han, Junwei Hu, Xintao |
| contents | The development of large language models (LLMs) is costly and has significant commercial value. Consequently, preventing unauthorized appropriation of open-source LLMs and protecting developers' intellectual property rights have become critical challenges. In this work, we propose the Functional Network Fingerprint (FNF), a training-free, sample-efficient method for detecting whether a suspect LLM is derived from a victim model, based on the consistency between their functional network activity. We demonstrate that models that share a common origin, even with differences in scale or architecture, exhibit highly consistent patterns of neuronal activity within their functional networks across diverse input samples. In contrast, models trained independently on distinct data or with different objectives fail to preserve such activity alignment. Unlike conventional approaches, our method requires only a few samples for verification, preserves model utility, and remains robust to common model modifications (such as fine-tuning, pruning, and parameter permutation), as well as to comparisons across diverse architectures and dimensionalities. FNF thus provides model owners and third parties with a simple, non-invasive, and effective tool for protecting LLM intellectual property. The code is available at https://github.com/WhatAboutMyStar/LLM_ACTIVATION. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22692 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FNF: Functional Network Fingerprint for Large Language Models Liu, Yiheng Ning, Junhao Xia, Sichen Sun, Haiyang Yang, Yang Chi, Hanyang Gao, Xiaohui Qiang, Ning Ge, Bao Han, Junwei Hu, Xintao Computation and Language Artificial Intelligence Cryptography and Security The development of large language models (LLMs) is costly and has significant commercial value. Consequently, preventing unauthorized appropriation of open-source LLMs and protecting developers' intellectual property rights have become critical challenges. In this work, we propose the Functional Network Fingerprint (FNF), a training-free, sample-efficient method for detecting whether a suspect LLM is derived from a victim model, based on the consistency between their functional network activity. We demonstrate that models that share a common origin, even with differences in scale or architecture, exhibit highly consistent patterns of neuronal activity within their functional networks across diverse input samples. In contrast, models trained independently on distinct data or with different objectives fail to preserve such activity alignment. Unlike conventional approaches, our method requires only a few samples for verification, preserves model utility, and remains robust to common model modifications (such as fine-tuning, pruning, and parameter permutation), as well as to comparisons across diverse architectures and dimensionalities. FNF thus provides model owners and third parties with a simple, non-invasive, and effective tool for protecting LLM intellectual property. The code is available at https://github.com/WhatAboutMyStar/LLM_ACTIVATION. |
| title | FNF: Functional Network Fingerprint for Large Language Models |
| topic | Computation and Language Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2601.22692 |