作者位次 #5/5ACL 2026Findings· Findings of ACL
Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models
Shuhao Zhang · Yuli Chen · Jiale Han · Bo Cheng · Jiabao Ma
摘要
Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text. Correspondingly, stealing watermark algorithms (SWAs) derive watermark information from watermarked texts generated by victim LLMs to craft highly targeted adver...