- bihe.zhao@cispa.de
- St. Ingbert, Germany
- github.com/BiheZhao
- Google Scholar
Third-year Ph.D. student at CISPA Helmholtz Center for Information Security. Research interests are trustworthy AI, data provenance for generative models, watermarking, and AI privacy.
Education
Ph.D., Computer Science
CISPA Helmholtz Center for Information SecuritySt. Ingbert, Germany
- Co-supervised by Prof. Adam Dziedzic and Prof. Franziska Boenisch (SprintML lab).
- Research on data provenance, membership and dataset inference, and watermarking for generative models.
M.Sc., Cyber Science and Technology
Beihang UniversityBeijing, China
- Co-advised by Prof. Zhenyu Guan and Prof. Song Bian.
Experience
Research Assistant
Agency for Science, Technology and Research (A*STAR)Singapore
- Proposed a drag-style editing scheme for neural radiance fields (NeRF) under user specification.
- Designed a matching algorithm to enforce multi-view consistency of the edited scene.
- Developed a generative model that edits the scene under correspondence supervision across views.
Research Intern
SenseTime ResearchBeijing, China
- Proposed a query-efficient model extraction attack based on public datasets that outperforms prior attacks by a large margin.
- Revealed a non-local self-similarity signal for face forgery detection and built a unified detection framework around it (IEEE SPL).
Backend Development Intern
ByteDanceBeijing, China
- Contributed to a data annotation and management platform.
- Developed and improved an alarm center with over 20,000 rules for detecting unusual data traffic, in Go.
Awards
First Prize, 12th National College Student Information Security Contest
Face-swap detection based on video watermarking and physical unclonable functions.
First Prize, Academic Excellence Award
Excellent Student
Outstanding Student President
Publications
See the publications page for the full list with abstracts and BibTeX.