Sungho Keum

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

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

Frequent co-authors

Leo Marchyok (1)Zachary Coalson (1)Sooel Son (1)Sanghyun Hong (1)

Papers (1)

Feb 19, 2026

Leo Marchyok +43w ago

Discovering Universal Activation Directions for PII Leakage in Language Models

Language models harbor hidden "PII leakage knobs" – universal activation directions that, when tweaked, dramatically increase the generation of sensitive personal information.

Leo Marchyok, Zachary Coalson, Sungho Keum +2

Constitutional AI & AI Ethics Interpretability & Mechanistic Interp Red-Teaming & Adversarial Robustness

Search

Sungho Keum

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)