Jeongyeon Hwang

Hi! I’m Jeongyeon Hwang, a fourth-year integrated M.S./Ph.D. candidate in the Graduate School of Artificial Intelligence at POSTECH, advised by Jungseul Ok.

My research focuses on auditing the adversarial robustness of language model systems. As LLMs become increasingly general-purpose and embedded in real-world systems, their robustness becomes harder to define and evaluate. I study how these systems fail under realistic adversarial conditions and develop methods to rigorously evaluate and improve their robustness.

Please feel free to reach out via email at {firstname}.{lastname}@postech.ac.kr.

News

Jun 2026Selected as a Doctoral Excellence Scholarship recipient by KOSAF.
May 2026A paper (BIRA) got accepted at ICML 2026.
Jan 2026Received an Honorable Mention at the BK21 Outstanding Paper Awards from POSTECH GSAI.
Sep 2025Starting as a visiting scholar at NYU (September–December).
Aug 2025Two papers (RA-RAG, LSC) got accepted at EMNLP 2025.
Aug 2024A paper (MedBN) got accepted at CVPR 2024.

Selected Publications

Language Model Fingerprinting Requires Rethinking Watermark Teachers

Jeongyeon Hwang, Anshul Nasery, Sewoong Oh, Jungseul Ok

arXiv 2026

Paper Code

LLM Watermark Evasion via Bias Inversion

Jeongyeon Hwang, Sangdon Park, Jungseul Ok

ICML 2026

Paper Code

Retrieval-Augmented Generation with Estimation of Source Reliability

Jeongyeon Hwang, Junyoung Park, Hyejin Park, Dongwoo Kim, Sangdon Park, Jungseul Ok

EMNLP, 2025 Main (long)

Paper Code

MedBN: Robust Test-Time Adaptation against Malicious Test Samples

Hyejin Park*, Jeongyeon Hwang*, Sunung Mun, Sangdon Park, Jungseul Ok

CVPR 2024

Paper Code