Jinseong Park

AI Fellow · Korea Institute for Advanced Study (KIAS)

Hi, I'm Jinseong Park. Starting Spring 2027, I will be joining the School of Cybersecurity at Korea University as an Assistant Professor, leading TrustML Lab. Until then, I am spending my gap year as an AI Fellow (AI Assistant Professor) at the Korea Institute for Advanced Study (KIAS).

My work focuses on trustworthy machine learning (TrustML), investigating theoretical foundations and practical algorithms for Privacy- and Safety preserving Intelligence (PSI, Ψ) systems. My research extends to industrial applications by designing scalable and robust systems through trustworthy AI.

I am seeking highly motivated collaborators and researchers. If you are interested in joining our group in Spring 2027, please send me an email with cv.

About Research Publications Contact

Research

🧠

Understanding of AI

We study the theoretical foundations of modern AI. Our goal is to understand how AI works.

Generative Modeling Generalization Memorization

🔒

Privacy & Safety Issues of AI

We develop privacy- and safety-preserving machine learning algorithms. Our work spans formal privacy guarantees via differential privacy, machine unlearning for generative AI, and defenses against AI attacks.

Differential Privacy Machine Unlearning Attack Robustness

📈

Industrial Applications

We apply trustworthy AI techniques to real-world industrial challenges.

Time Series Finance Manufacturing

View full research overview →

Latest News

Jul 2026 Starting Spring 2027, I will be joining the School of Cybersecurity at Korea University as an Assistant Professor.

Jun 2026 One paper on "diffusion bridge" was accepted at KDD 2026. See you in Jeju!

May 2026 I will give a tutorial talk on diffusion models at KIAS CAC Summer School [Link].

May 2026 One paper on "stability analysis on optimization" was accepted at ICML 2026. See you in Seoul!

Feb 2026 At KIAS, I have been promoted to AI Fellow (AI Assistant Professor), starting March 2026.