Scholar
Sanghyun Hong
Google Scholar ID: 664LW90AAAAJ
Assistant Professor of Computer Science, Oregon State University
Privacy
Security
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,792
H-index
16
i10-index
19
Publications
20
Co-authors
19
list available
Publications
18 items
Do Reasoning Representations Help Humans Evaluate LLM Outputs?
2026
Cited
0
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
2026
Cited
0
On the Resilience of Text-to-Video Diffusion Models to Hardware Faults
2026
Cited
0
When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
2026
Cited
0
Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
2026
Cited
0
Fail-Closed Alignment for Large Language Models
2026
Cited
0
Discovering Universal Activation Directions for PII Leakage in Language Models
2026
Cited
0
Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
2025
Cited
0
Load more
Co-authors
15 total
Yigitcan Kaya
Postdoc at UC Santa Barbara
Nicholas Carlini
Anthropic
Alexey Kurakin
Research Software Engineer, Google Brain
Florian Tramèr
Assistant Professor of Computer Science, ETH Zurich
Nicolas Papernot
University of Toronto and Vector Institute
Dana Dachman-Soled
Associate Professor, Department of Electrical and Computer Engineering, University of Maryland
Niklas Elmqvist
Villum Investigator and Professor of Computer Science, Aarhus University
Sungbok Shin
Aarhus University
