Tran Huynh
3 papers
· 2024–2024
· 3 conferences
· across top CS/AI conferences
Achievements
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (1)
ECCV (1)
EMNLP (1)
Top co-authors
Keywords
backdoor attack
(2)
adversarial learning
(2)
adversarial training
(1)
instruction tuning
(1)
surrogate model
(1)
bi-level optimization
(1)
trigger pattern
(1)
embedding perturbation
(1)
clean-label attack
(1)
alternating training
(1)
harmful content mitigation
(1)
backdoor removal
(1)
safety backdoor
(1)
adversarial machine learning
(1)