AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing

• URL: http://arxiv.org/abs/2605.29434v1
• Date: Thu, 28 May 2026 06:30:43 GMT
• Title: AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
• Abstract summary: AliMark is a framework that reformulates sentence-level watermarking as a bit sequence encoding and alignment problem.<n>We show that AliMark substantially outperforms state-of-the-art baselines under diverse paraphrasing attacks.
• Score: 55.03371974830747
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and merging, which commonly arise under strong paraphrasers like DIPPER and GPT-3.5. To mitigate this issue, we propose AliMark, a framework that reformulates sentence-level watermarking as a bit sequence encoding and alignment problem between a potentially watermarked text and a secret bit sequence. Notably, our approach adopts a two-stage detection strategy: we generate multiple restructured text variants and adaptively align their extracted bit sequences with the secret bit sequence to minimize alignment cost. This multi-candidate alignment design naturally improves robustness to sentence merges and splits. Extensive experiments demonstrate that AliMark substantially outperforms state-of-the-art baselines under diverse paraphrasing attacks.

Related papers

• SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness [71.08096624551246]
  robustness to paragraph-level paraphrasing remains difficult because such attacks globally disrupt watermark signals by changing sentence order.<n>We propose SAMark, a self-anchored watermarking framework that removes the dependency on sentence order by establishing a step-independent green region in semantic space.<n> Experimental results show that SAMark achieves up to 90.2% TP@FP1% under typical paragraph-level paraphrasing attacks.
  arXiv  Detail & Related papers  (2026-05-25T12:46:15Z)
• SWAN: Semantic Watermarking with Abstract Meaning Representation [61.15962841972814]
  SWAN (Semantic Watermarking with Abstract Meaning Representation) is a novel framework that embeds watermark signatures into the semantic structure of a sentence.<n>As the signature is encoded at the semantic structure level, any paraphrase that preserves meaning automatically preserves the signature.
  arXiv  Detail & Related papers  (2026-05-05T21:13:30Z)
• PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints [49.2373408329323]
  We introduce a new theoretical framework on watermark-leveling (SWM) for large language models (LLMs)<n>We propose PMark, a simple yet powerful SWM method that estimates the median next sentence dynamically through sampling channels.<n> Experimental results show that PMark consistently outperforms existing SWM baselines in both text quality and paraphrasing.
  arXiv  Detail & Related papers  (2025-09-25T12:08:31Z)
• CoheMark: A Novel Sentence-Level Watermark for Enhanced Text Quality [15.40847234599879]
  CoheMark exploits the cohesive relationships between sentences for better logical fluency.<n>CoheMark achieves strong watermark strength while exerting minimal impact on text quality.
  arXiv  Detail & Related papers  (2025-04-24T07:08:13Z)
• Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning [34.76886510334969]
  A piggyback attack can maliciously alter the meaning of watermarked text-transforming it into hate speech-while preserving the original watermark.<n>We propose a semantic-aware watermarking algorithm that embeds watermarks into a given target text while preserving its original meaning.
  arXiv  Detail & Related papers  (2025-04-09T04:38:17Z)
• DERMARK: A Dynamic, Efficient and Robust Multi-bit Watermark for Large Language Models [18.023143082876015]
  We propose a dynamic, efficient, and robust multi-bit watermarking method that divides the text into variable-length segments for each watermark bit.<n>Our method reduces the number of tokens required per embedded bit by 25%, reduces watermark embedding time by 50%, and maintains high robustness against text modifications and watermark erasure attacks.
  arXiv  Detail & Related papers  (2025-02-04T11:23:49Z)
• SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation [72.10931780019297]
  Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. We propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive hashing (LSH) Experimental results show that our novel semantic watermark algorithm is not only more robust than the previous state-of-the-art method on both common and bigram paraphrase attacks, but also is better at preserving the quality of generation.
  arXiv  Detail & Related papers  (2023-10-06T03:33:42Z)
• Tracing Text Provenance via Context-Aware Lexical Substitution [81.49359106648735]
  We propose a natural language watermarking scheme based on context-aware lexical substitution. Under both objective and subjective metrics, our watermarking scheme can well preserve the semantic integrity of original sentences.
  arXiv  Detail & Related papers  (2021-12-15T04:27:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.