作者位次 #2/5ACL 2026Findings· Findings of ACL
Measuring Watermarking under Jailbreaking: ASR Inflation and Goal-Compliance Mismatch
Sungwoo Han · Sangjun Moon · Jingun Kwon · Hidetaka Kamigaito · Manabu Okumura
摘要
Recently, watermarking has attracted growing attention as a practical technique for source attribution of machine-generated text. However, most prior work studies watermarking under benign prompts, while its behavior under jailbreaking prompts remains underexplored. This gap matters because jailb...