Yang Jing

Yang Jing

Ph.D. Student in Data Science · AI Safety

AI SAFETY · TRUSTWORTHY GENERATIVE AI

Hi, I’m Yang Jing.

I am a first-year Ph.D. student in the Department of Data Science at City University of Hong Kong, advised by Prof. Kaidi Xu. My research focuses on making AI systems safer, more trustworthy, and more robust, with particular interests in generative AI safety and deepfake detection.

Research Interests

AI Safety — Robustness, reliability, and responsible behavior of modern AI systems.
Generative AI Security — Privacy protection and anti-personalization for text-to-image diffusion models.
Deepfake Detection — Generalizable detection methods across diverse manipulation scenarios.

Selected Publications

GM-DF: Generalized Multi-Scenario Deepfake Detection

Yang Jing (third author), et al.
ACM Multimedia (ACM MM), 2025.
Paper · All publications

DTIA: Disruptive Text-Image Alignment for Countering Text-to-Image Diffusion Model Personalization

Ya Gao, Jing Yang (co-first author), et al.
Data Science and Engineering, 2024.
Paper

DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Model

Yang Jing, et al.
IEEE International Joint Conference on Biometrics (IJCB), Oral, 2024.
Paper

Education

  • Ph.D. in Data Science, City University of Hong Kong, 2026–present
  • M.S. in Computer Science and Technology, Northwestern Polytechnical University, 2022–2025
  • B.S. in Computer Science and Technology, Minzu University of China, 2019–2022

Experience & Recognition

  • Research Assistant, Great Bay University
  • Kaggle Stable Diffusion — Image to Prompts, Top 4%