SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models
The rapid proliferation of large language models (LLMs) has created an urgent need for reliable methods to detect whether a text is generated by such models. In this paper, we propose SimMark, a posthoc watermarking algorithm that makes LLMs' outputs traceable without requiring access to the model's internal logits, enabling compatibility with a wide range of LLMs, including API-only models. By leveraging the similarity of semantic sentence embeddings and rejection sampling to impose detectable statistical patterns imperceptible to humans, and employing a soft counting mechanism, SimMark achieves robustness against paraphrasing attacks. Experimental results demonstrate that SimMark sets a new benchmark for robust watermarking of LLM-generated content, surpassing prior sentence-level watermarking techniques in robustness, sampling efficiency, and applicability across diverse domains, all while preserving the text quality.
Code (1)
Tasks
SentenceSentence EmbeddingsSimilar Papers 제목 키워드 기반
SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level semantic watermarking algorithm based on loca…
SentenceText GenerationAliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
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 se…
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remains difficult because such attacks globall…
SWAN: Semantic Watermarking with Abstract Meaning Representation
We introduce SWAN (Semantic Watermarking with Abstract Meaning Representation), a novel framework that embeds watermark signatures into the semantic structure of a sentence using Abstract Meaning Representation (AMR). In…
Text GenerationPMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing attacks by treating the sentence as the fundamental unit. However, existing …