{"ID":6536387,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T08:33:44.272455028Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10210","arxiv_id":"2607.10210","title":"Toward Stronger Code Watermarking: A Grammar-Driven Approach to Optimizing the Trade-off Between Quality and Detectability","abstract":"With the rapid development of Large Language Models (LLMs), text watermarking has emerged as a crucial technique for identifying machine-generated content. However, directly applying existing logits-based watermarking methods to code generation remains challenging, since the low-entropy nature of code exacerbates the trade-off between code quality and watermark detectability. In this paper, we propose a novel code watermarking approach called Grammar-Driven Watermark (GDW) for LLMs. GDW preserves syntactic validity through a grammar-guided three-level masking mechanism and injects watermark signals via structural role-aware modulation, assigning a stronger bias to content-bearing tokens while applying a more conservative bias to syntax-critical tokens. Aligning with the generation process, we further design a role-aware weighted detection statistic to improve detectability. Experiments across multiple programming languages, models, and decoding strategies show that GDW establishes a stronger quality-detectability trade-off frontier than existing methods, while maintaining robustness against variable-renaming attacks.","short_abstract":"With the rapid development of Large Language Models (LLMs), text watermarking has emerged as a crucial technique for identifying machine-generated content. However, directly applying existing logits-based watermarking methods to code generation remains challenging, since the low-entropy nature of code exacerbates the t...","url_abs":"https://arxiv.org/abs/2607.10210","url_pdf":"https://arxiv.org/pdf/2607.10210v1","authors":"[\"Licheng Yu\",\"Aiwei Liu\",\"Songze Li\"]","published":"2026-07-11T08:43:15Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}