Jihye Choi
5 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🧭
Keyword Pioneer
🌍
Conference Polyglot
(4)
🐝
Cross-Pollinator
(10)
🌉
Interdisciplinary Bridge
Conferences
ICML (2)
ACL (1)
ICLR (1)
MLHC (1)
Top co-authors
Keywords
adversarial robustness
(1)
concept-based explanation
(1)
adversarial training
(1)
ai safety
(1)
distribution shift
(1)
selective classification
(1)
adversarial attack
(1)
deep neural network
(1)
adversarial perturbation
(1)
out-of-distribution detection
(1)
jailbreak attack
(1)
rejection option
(1)
perturbation magnitude
(1)
guard model
(1)
large language model
(1)
Papers
CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
ICLR 2025
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
ACL 2024
MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance
MLHC 2024
Stratified Adversarial Robustness with Rejection
ICML 2023
Concept-based Explanations for Out-of-Distribution Detectors
ICML 2023