Unified attacks to large language model watermarks: Spoofing and scrubbing in unauthorized knowledge distillation

Open Webpage

Xin Yi, Yue Li, Shunfan Zheng, Linlin Wang, Xiaoling Wang, Liang He

Published: 2025, Last Modified: 25 Jan 2026Knowl. Based Syst. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0