arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Xunguang Wang"" — arXiv2 Search
Showing 1–2 of 2 results
/ Date
/ Name
Mar 23, 2025
STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models
Jun 8, 2024
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner