Jungwoo Park

DMIS Lab, Korea University

Papers on Lattice

Total citations

Topics

h-index

Research focus

Interpretability & Mechanistic Interp (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Yein Park (1)Jaewoo Kang (1)

Papers (1)

Sep 30, 2025

ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

Mechanistic analysis reveals how adversarial suffixes suppress the propagation of refusal-mediating directions in LLMs, and ASGuard offers a targeted intervention.

Yein Park, Jungwoo Park, Jaewoo Kang

Interpretability & Mechanistic Interp Red-Teaming & Adversarial Robustness

Search

Jungwoo Park

Research focus

Frequent co-authors

Papers (1)