Skip to main content
Search

City University of Macau

1 related articles

Subscribe to updates
  1. arXiv

    Open-source LLM watermarking moves to a private vocabulary: injected once on Alpaca, SAME keeps a 100% fixed trigger rate after downstream fine-tuning

    Once open-source model weights are public, third-party fine-tuning rewrites parameters and internal representations, breaking watermarks that rely on specific trigger words or parameter traces. SAME pairs every native token with a fixed private embedding and uses dual-path training so the private vocabulary inherits native semantics, tying the watermark to the model's evolving semantic ability. Injected once on Alpaca into Qwen3-8B-Instruct, it keeps a 100% fixed trigger rate after independent fine-tuning on SST-2, AG News, MMLU and BoolQ, while BadEdit falls to 10.87% on MMLU.

You’re all caught up