Kai Williams
2 papers
· 2024–2024
· 2 conferences
· across top CS/AI conferences
Achievements
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(2)
🐝
Cross-Pollinator
(6)
🐣
Hot Topic Early Bird
Conferences
EMNLP (1)
NIPS (1)
Top co-authors
Keywords
adversarial defense
(2)
fine-tuning attack
(2)
large language model
(2)
harmful fine-tuning
(2)
model safety
(1)
harmful content
(1)
representation noising
(1)
defense mechanism
(1)
llm safety
(1)
representation learning
(1)
model defense
(1)
adversarial learning
(1)
model security
(1)
model robustness
(1)