@inproceedings{yan-etal-2026-duffin,
    title = "{D}u{FF}in: A Dual-Level Fingerprinting Framework for {LLM}s {IP} Protection",
    author = "Yan, Yuliang  and
      Tang, Haochun  and
      Yan, Shuo  and
      Dai, Enyan",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.273/",
    pages = "5168--5184",
    ISBN = "979-8-89176-386-9",
    abstract = "Large language models (LLMs) are considered valuable Intellectual Properties (IP) due to the enormous computational cost of training, making their protection against malicious stealing or unauthorized deployment crucial.Despite efforts in watermarking and fingerprinting, existing methods either affect text generation or rely on white-box access, limiting practicality.To address this, we propose DuFFin, a novel Dual-Level Fingerprinting framework for black-box ownership verification.DuFFin jointly extracts trigger patterns and knowledge-level fingerprints to identify the source of a suspect model.We conduct experiments on diverse open-source models, including four popular base LLMs and their fine-tuned, quantized, and safety-aligned variants released by large companies, start-ups, and individuals.Results show that DuFFin accurately verifies the copyright of protected LLMs on their variants, achieving an IP-ROC greater than 0.99.Our code is available at https://github.com/yuliangyan0807/llm-fingerprint."
}