Pith. sign in

REVIEW 7 cited by

An Entropy-based Text Watermarking Detection Method

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.13485 v4 pith:GKUM5UFI submitted 2024-03-20 cs.CL

classification cs.CL
keywords detectiontexttextbfwatermarkingentropyscenarioswatermarkalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Text watermarking algorithms for large language models (LLMs) can effectively identify machine-generated texts by embedding and detecting hidden features in the text. Although the current text watermarking algorithms perform well in most high-entropy scenarios, its performance in low-entropy scenarios still needs to be improved. In this work, we opine that the influence of token entropy should be fully considered in the watermark detection process, $i.e.$, the weight of each token during watermark detection should be customized according to its entropy, rather than setting the weights of all tokens to the same value as in previous methods. Specifically, we propose \textbf{E}ntropy-based Text \textbf{W}atermarking \textbf{D}etection (\textbf{EWD}) that gives higher-entropy tokens higher influence weights during watermark detection, so as to better reflect the degree of watermarking. Furthermore, the proposed detection process is training-free and fully automated. From the experiments, we demonstrate that our EWD can achieve better detection performance in low-entropy scenarios, and our method is also general and can be applied to texts with different entropy distributions. Our code and data is available\footnote{\url{https://github.com/luyijian3/EWD}}. Additionally, our algorithm could be accessed through MarkLLM \cite{pan2024markllm}\footnote{\url{https://github.com/THU-BPM/MarkLLM}}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm

    cs.CR 2025-09 conditional novelty 7.0 of 10

    A trigger-tag watermark embedded by fine-tuning lets modified LLMs mark their own phishing outputs for cheap detection.

  2. SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

    cs.CR 2026-05 unverdicted novelty 6.5 of 10

    SAMark uses self-anchored semantic green regions, multi-channel hyperbolic scoring, and diversity-aware filtering to reach 90.2% TP@FP1% detection under paragraph paraphrasing while preserving text quality.

  3. Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness

    cs.CR 2025-06 conditional novelty 6.0 of 10

    A context-aware plug-in for LLM watermarking that skips or weakens watermarks on semantically critical tokens, improving task accuracy at similar detection rates.

  4. Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack

    cs.CR 2025-06 conditional novelty 6.0 of 10

    LBW embeds watermarks into autoregressive image token maps by biasing token sampling toward a secret green list and detects them with a z-test on green-token counts.

  5. Toward Stronger Code Watermarking: A Grammar-Driven Approach to Optimizing the Trade-off Between Quality and Detectability

    cs.CR 2026-07 conditional novelty 5.5 of 10

    Grammar-guided three-level masking plus role-aware logit bias and weighted detection improves the code quality–watermark detectability frontier over KGW, SWEET, EWD, STONE, CodeIP, and SynthID-Text.

  6. Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models

    cs.CL 2025-08 conditional novelty 5.0 of 10

    Removing tokens that would not survive re-tokenization at generation time fixes steganographic extraction errors and slightly improves watermark detectability.

  7. Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey

    cs.CL 2025-02 conditional novelty 4.0 of 10

    A survey organizes current research on trustworthy RAG into six pillars, reliability, privacy, safety, fairness, explainability, and accountability, and maps methods, metrics, and open problems for each.

Pith tools