Zhifei Zheng
3 papers
· 2023–2025
· 2 conferences
· across top CS/AI conferences
Achievements
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(10)
Conferences
IJCAI (2)
EMNLP (1)
Top co-authors
Keywords
harmful content
(1)
safety alignment
(1)
model alignment
(1)
branch and bound
(1)
exact algorithm
(1)
lower bound
(1)
jailbreak attack
(1)
search space
(1)
np-hard problem
(1)
upper bound
(1)
llm safety
(1)
harmful knowledge
(1)
graph reduction
(1)
threat assessment
(1)
minimum dominating set
(1)
harmfulness judgment
(1)