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

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing arXiv:2605.29434v1 Announce Type: cross 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 AliMa