Lune

ACL Findings2026

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework

Zhuoshang Wang, Yubing Ren, Yanan Cao, Fang Fang, Xiaoxue Li, Li Guo

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 nonintrusive, 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense cites Provable Robust Watermarking for AI-Generated Text
  • Provable Robust Watermarking for AI-Generated Text cites Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
  • Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense cites A Watermark for Large Language Models
  • Unbiased Watermark for Large Language Models cites Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
  • Unbiased Watermark for Large Language Models cites A Watermark for Large Language Models
  • Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level Watermarking cites Provable Robust Watermarking for AI-Generated Text
  • Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level Watermarking cites A Watermark for Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Towards Reliable Marking and Verification of AI-Generated Text via Geometry-aware Sentence-level WatermarkingYubing Ren, Ping Guo, Yanan CaoICML 2026

Builds on20

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. A Watermark for Large Language ModelsJohn Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz et al.ICML 2023 · 854 citations
  3. Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defenseKalpesh Krishna, Yixiao Song, Marzena Karpinska, John Wieting et al.NeurIPS 2023 · 657 citations
  4. Provable Robust Watermarking for AI-Generated TextXuandong Zhao, Prabhanjan Vijendra Ananth, Lei Li, Yu-Xiang WangICLR 2024 · 312 citations
  5. Unbiased Watermark for Large Language ModelsZhengmian Hu, Lichang Chen, Xidong Wu, Yihan Wu et al.ICLR 2024 · 103 citations

Related papers

  1. PVMark: Enabling Public Verifiability for LLM Watermarking SchemesHaohua Duan, Liyao Xiang, Xin Zhang, Baochun Li et al.USENIX Security 2026 · 2 citations
  2. Black-Box Detection of Language Model WatermarksThibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. VechevICLR 2025
  3. HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy DistributionsDor Tsur, Carol Xuan Long, Claudio Mayrink Verdun, Sajani Vithana et al.NeurIPS 2025 · 9 citations
  4. RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language ModelsPeizhuo Lv, Mengjie Sun, Hao Wang, XiaoFeng Wang et al.CCS 2025
  5. Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMsZhihao Wu, Gracia Gong, Qinglin Zhu, Yudong Chen et al.ICML 2026
Dusk over the sea between two cliffs drawn in fine vertical lines