1
LLM Watermark Evasion via Bias Inversion
黑盒环境下LLM水印逃避新突破：理论揭示重写型攻击无需查询即可规避检测，且不损语义完整性，为AI内容溯源安全敲响警钟。
arXiv:2509.23019v5 Announce Type: replace-cross Abstract: Watermarking offers a promising solution for detecting LLM-generated content, yet its robust…