SynMark: Semantic-Coordinate Multi-Bit Watermarking during LLM Code Generation

Summary

SynMark is a multi-bit watermarking method for LLM-generated code that replaces surface-token routing with learned semantic coordinates, so identifier renaming does not desynchronize message routing. It uses a syntax-aware adaptive bias during generation and reliability-weighted aggregation during extraction. Under 100% identifier renaming it retains 82.27% BitAcc on CodeLlama and 83.77% on DeepSeek-Coder, and across three code LMs it improves clean BitAcc and Pass@1 by up to 4.53 and 11.18 percentage points over the strongest watermarked baselines.