Junxiao Yang
3 papers
· 2024–2026
· 2 conferences
· across top CS/AI conferences
Achievements
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(8)
🌍
Conference Polyglot
(2)
🏆
Keyword Champion
(2)
Conferences
ACL (2)
AAAI (1)
Top co-authors
Keywords
jailbreaking attack
(2)
instruction following
(1)
safety alignment
(1)
adversarial attack
(1)
jailbreak attack
(1)
goal prioritization
(1)
attack success rate
(1)
llm security
(1)
large language model
(1)
semantic cognition
(1)
safety defense
(1)
gradient-based optimization
(1)
emoji-triggered toxicity
(1)