Scholar
Zhanhao Hu
Google Scholar ID: PGdm9MUAAAAJ
University of California, Berkeley
large language models
adversarial examples
privacy
security
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
431
H-index
9
i10-index
9
Publications
19
Co-authors
0
Publications
10 items
Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling
2026
Cited
0
Twin Agent: Context Residual Compression for Privilege Separated Agents
2026
Cited
0
Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies
2026
Cited
0
GradShield: Alignment Preserving Finetuning
2026
Cited
0
Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern
2026
Cited
0
A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical World
2025
Cited
0
Better Privilege Separation for Agents by Restricting Data Types
2025
Cited
0
JULI: Jailbreak Large Language Models by Self-Introspection
2025
Cited
0
Load more
