me.jpeg

Zhanhao Hu 胡展豪

Postdoc at UC Berkeley

Contact:
zhanhaohu[DOT]cs[AT]gmail[DOT]com
Google Scholar   Github

Affiliation:
Department of Electrical Engineering and Computer Sciences (EECS),
Institute for Data Science (BIDS),
UC Berkeley, California, 94720


I am a postdoc in the Department of Electrical Engineering and Computer Sciences (EECS) at UC Berkeley, advised by Prof. David Wagner. I received my Ph.D. in Computer Science and Technology from Tsinghua University in 2023, advised by Prof. Bo Zhang and Prof. Xiaolin Hu. I received my Bachelor’s degree in Mathematics and Physics from Tsinghua University in 2017. My current research interest primarily includes adversarial examples and privacy in deep learning, especially in Computer Vision (CV) and Large Language Models (LLMs). My goal is to contribute to the development of reliable and trustworthy AI systems by identifying and tackling anomalous behavior in deep learning models.


selected publications

  1. CVPR
    Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling
    Zhanhao Hu, Wenda Chu, Xiaopei Zhu, Hui Zhang, Bo Zhang, and Xiaolin Hu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    2023natural.jpg
  2. CVPR
    Oral
    Adversarial Texture for Fooling Person Detectors in the Physical World
    Zhanhao Hu, Siyuan Huang, Xiaopei Zhu, Fuchun Sun, Bo Zhang, and Xiaolin Hu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    2022texture.jpg
  3. CVPR
    Oral
    Infrared Invisible Clothing: Hiding from Infrared Detectors at Multiple Angles in Real World
    Xiaopei Zhu, Zhanhao Hu, Siyuan Huang, Jianmin Li, and Xiaolin Hu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    2022infrared.jpg