Skip to content

Bypassing Safety Alignment via API Design: A Systematic Risk Analysis of Response Prefill in LLM Systems.

Yakai Li, Jiekang Hu, Weiduan Sang, Luping Ma, Dongsheng Nie, Weijuan Zhang, Aimin Yu, Yi Su, Qingjia Huang, Qihang Zhou

VenueADSN
Year2026
ProceedingsDSN

Browse the full DSN paper archive.