Exploring AI Security, Trustworthy LLMs, and AGI Safety
Detecting and mitigating backdoor attacks targeting the reasoning capabilities of Large Language Models.
Developing robust detection and defense mechanisms against adversarial attacks on vision and language models.
Building reliable and safe AI systems for deployment in high-stakes environments.
Researching systematic approaches to ensure AI systems behave as intended and remain aligned with human values.
arXiv:2601.08511 (Submitted to ACL 2026)
View PaperThe 30th Pacific-Asia Conference on Knowledge Discovery and Data Mining(PAKDD 2026)
IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS 2025)
View PaperJournal of the Korea Institute of Information Security & Cryptology (2024): 493-503.
View Paper