Bio

Jung-Eun Kim is an Assistant Professor in the Department of Computer Science at NC State University. She conducts fundamental AI/machine learning research, especially on Trustworthy, Interpretable, and Efficient AI/deep learning. Her research interests lie at the intersection of failure modes/safety risks/vulnerabilities and efficiency of deep learning. Before joining NC State, she was an associate research scientist in Computer Science at Yale University. She received her PhD in Computer Science from the University of Illinois at Urbana-Champaign, and BS and MS degrees in Computer Science and Engineering from Seoul National University, Seoul, Korea.

Area(s) of Expertise

Trustworthy, Interpretable, and Efficient AI/deep learning

Publications

• Backdoor Containment via Expert Quarantine and Shutdown in LLMs , arXiv (Cornell University) (2026)
• Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection , arXiv (Cornell University) (2026)
• Decoupling Generalizability and Membership Privacy Risks in Neural Networks , arXiv (Cornell University) (2026)
• Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights , arXiv (Cornell University) (2026)
• Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference , arXiv (Cornell University) (2026)

View all publications

Grants

View all grants