Signature filtering learns unreliable tokens with MILP and removes them at detection time, raising true positive rates from 8-31% to 78-99% across Kgw, Sweet, Unigram, and Exp watermarks on multiple corpora and LLMs while controlling false positives.
10 AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing Fu, Y ., Xiong, D., and Dong, Y
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
AliMark introduces a two-stage detection strategy with multi-candidate bit sequence alignment to improve robustness of sentence-level text watermarks against paraphrasing attacks.
citing papers explorer
-
Signature filtering: a lightweight enhancement for statistical watermark detection in large language models
Signature filtering learns unreliable tokens with MILP and removes them at detection time, raising true positive rates from 8-31% to 78-99% across Kgw, Sweet, Unigram, and Exp watermarks on multiple corpora and LLMs while controlling false positives.
-
AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
AliMark introduces a two-stage detection strategy with multi-candidate bit sequence alignment to improve robustness of sentence-level text watermarks against paraphrasing attacks.