Zhanhao Hu
Scholar

Zhanhao Hu

Google Scholar ID: PGdm9MUAAAAJ
University of California, Berkeley
large language modelsadversarial examplesprivacysecurity
Citations & Impact
All-time
Citations
429
 
H-index
9
 
i10-index
9
 
Publications
19
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • Publications:
  • - Neurips Spotlight: Toxicity Detection for Free
  • - CVPR 2023: Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling
  • - CVPR Oral 2022: Adversarial Texture for Fooling Person Detectors in the Physical World
  • - CVPR Oral 2022: Infrared Invisible Clothing: Hiding from Infrared Detectors at Multiple Angles in Real World
Research Experience
  • Currently a postdoc in the Department of Electrical Engineering and Computer Sciences (EECS) at UC Berkeley, advised by Prof. David Wagner.
Education
  • Ph.D. in Computer Science and Technology from Tsinghua University in 2023, advised by Prof. Bo Zhang and Prof. Xiaolin Hu; also worked with Prof. Jun Zhu and Prof. Jianming Li. Bachelor’s degree in Mathematics and Physics from Tsinghua University in 2017.
Background
  • Research interests include safety and robustness in deep learning, especially in Computer Vision (CV) and Large Language Models (LLMs), such as adversarial examples, jailbreaking, and prompt injection. The goal is to contribute to the development of reliable and trustworthy future AI systems by identifying and tackling anomalous behavior in deep learning models.
Miscellany
  • Profile picture taken by Kexin.
Co-authors
0 total
Co-authors: 0 (list not available)