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
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}}.
Forward citations
Cited by 7 Pith papers
-
Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
A trigger-tag watermark embedded by fine-tuning lets modified LLMs mark their own phishing outputs for cheap detection.
-
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
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.
-
Enhancing Watermarking Quality for LLMs via Contextual Generation States Awareness
A context-aware plug-in for LLM watermarking that skips or weakens watermarks on semantically critical tokens, improving task accuracy at similar detection rates.
-
Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack
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.
-
Toward Stronger Code Watermarking: A Grammar-Driven Approach to Optimizing the Trade-off Between Quality and Detectability
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.
-
Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models
Removing tokens that would not survive re-tokenization at generation time fixes steganographic extraction errors and slightly improves watermark detectability.
-
Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey
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.
Discussion (0). Continue with ORCID to comment.