{"ID":2833414,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.03620","arxiv_id":"2512.03620","title":"SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting","abstract":"The protection of Intellectual Property (IP) in Large Language Models (LLMs) represents a critical challenge in contemporary AI research. While fingerprinting techniques have emerged as a fundamental mechanism for detecting unauthorized model usage, existing methods -- whether behavior-based or structural -- suffer from vulnerabilities such as false claim attacks or susceptible to weight manipulations. To overcome these limitations, we propose SELF, a novel intrinsic weight-based fingerprinting scheme that eliminates dependency on input and inherently resists false claims. SELF achieves robust IP protection through two key innovations: 1) unique, scalable and transformation-invariant fingerprint extraction via singular value and eigenvalue decomposition of LLM attention weights, and 2) effective neural network-based fingerprint similarity comparison based on few-shot learning and data augmentation. Experimental results demonstrate SELF maintains high IP infringement detection accuracy while showing strong robustness against various downstream modifications, including quantization, pruning, and fine-tuning attacks. Our code is available at https://github.com/HanxiuZhang/SELF_v2.","short_abstract":"The protection of Intellectual Property (IP) in Large Language Models (LLMs) represents a critical challenge in contemporary AI research. While fingerprinting techniques have emerged as a fundamental mechanism for detecting unauthorized model usage, existing methods -- whether behavior-based or structural -- suffer fro...","url_abs":"https://arxiv.org/abs/2512.03620","url_pdf":"https://arxiv.org/pdf/2512.03620v1","authors":"[\"Hanxiu Zhang\",\"Yue Zheng\"]","published":"2025-12-03T09:53:47Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.AI\",\"cs.CL\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":606322,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2833414,"paper_url":"https://arxiv.org/abs/2512.03620","paper_title":"SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting","repo_url":"https://github.com/HanxiuZhang/SELF_v2","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}