paper-with-me

Papers

WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents

2024-09-08 · Leyi Pan, Aiwei Liu, Yijian Lu, Zitian Gao, Yichen Di, Shiyu Huang, Lijie Wen, Irwin King, Philip S. Yu

Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fully watermarked text from non-watermarked text, overlooking real-world scenarios where LLMs generate only small sections within large documents. In this scenario, balancing time complexity and detection performance poses significant challenges. This paper presents WaterSeeker, a novel approach to efficiently detect and locate watermarked segments amid extensive natural text. It first applies an efficient anomaly extraction method to preliminarily locate suspicious watermarked regions. Following this, it conducts a local traversal and performs full-text detection for more precise verification. Theoretical analysis and experimental results demonstrate that WaterSeeker achieves a superior balance between detection accuracy and computational efficiency. Moreover, its localization capability lays the foundation for building interpretable AI detection systems. Our code is available at https://github.com/THU-BPM/WaterSeeker.

📄 PDF Abstract BibTeX arXiv:2409.05112

Code (1)

thu-bpm/waterseeker 공식 구현 pytorch

Tasks

Computational EfficiencyText Detection

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Efficiently Identifying Watermarked Segments in Mixed-Source Texts

2024-10-04 · Xuandong Zhao, Chenwen Liao, Yu-Xiang Wang, Lei LI

Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily f…

Fast segmentation of watermarked texts from large language models through an epidemic change-point framework

2025-09-25 · Soham Bonnerjee, Subhrajyoty Roy, Sayar Karmakar arxiv

With the growing use of large language models, concerns over content authenticity have spurred a variety of watermarking schemes. These schemes use secret keys to detect machine-generated text while remaining imperceptib…

Bypassing LLM Watermarks with Color-Aware Substitutions

2024-03-19 · Qilong Wu, Varun Chandrasekaran

Watermarking approaches are proposed to identify if text being circulated is human or large language model (LLM) generated. The state-of-the-art watermarking strategy of Kirchenbauer et al. (2023a) biases the LLM to gene…

Language ModelingLanguage ModellingLarge Language Model

Watermark Anything with Localized Messages

2024-11-11 · Tom Sander, Pierre Fernandez, Alain Durmus, Teddy Furon 외

Image watermarking methods are not tailored to handle small watermarked areas. This restricts applications in real-world scenarios where parts of the image may come from different sources or have been edited. We introduc…

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

2026-03-16 · Zhuoshang Wang, Yubing Ren, Yanan Cao, Fang Fang 외 arxiv

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 verificat…