@inproceedings{wang-etal-2026-rethinking-llm,
    title = "Rethinking {LLM} Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework",
    author = "Wang, Zhuoshang  and
      Ren, Yubing  and
      Cao, Yanan  and
      Fang, Fang  and
      Li, Xiaoxue  and
      Guo, Li",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.990/",
    pages = "19773--19790",
    ISBN = "979-8-89176-395-1",
    abstract = "While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific detectors for verification. This dependency creates a fundamental barrier for real-world governance, as independent auditing becomes impossible without compromising model security or relying on the opaque claims of service providers. To resolve this dilemma, we introduce TTP-Detect, a pioneering black-box framework designed for non-intrusive, third-party watermark verification. By decoupling detection from injection, TTP-Detect reframes verification as a relative hypothesis testing problem. It employs a proxy model to amplify watermark-relevant signals and a suite of complementary relative measurements to assess the alignment of the query text with watermarked distributions. Extensive experiments across representative watermarking schemes, datasets and models demonstrate that TTP-Detect achieves superior detection performance and robustness against diverse attacks."
}