Ph.D. Student · Trustworthy AIGC

Kun Xu 许锟

I study generative model security, uncertainty, and trustworthy AI, with a focus on concept-level risks in text-to-image generation and deepfake detection.

I expect to receive my Ph.D. in October 2026 and am currently seeking postdoctoral or faculty positions.

  • NUAAPh.D. at Cyberspace Security
  • MilanoVisiting Ph.D. scholar in Italy
  • FocusGenerative concept security

About

A research profile built around safer generative AI.

I am a Ph.D. student at Nanjing University of Aeronautics and Astronautics, advised by Prof. Yushu Zhang. I am currently studying as a visiting Ph.D. scholar in Milano, Italy, under the supervision of Prof. Elena Ferrari.

My work explores generative concept security, uncertainty analysis, causal analysis, personalized text-to-image generation, content toxicity detection, diffusion models, and foundation models.

Research

Research themes

A compact map of the topics that connect my current work.

News

Recent updates

Selected milestones, submissions, talks, and awards.

Publications

Publications and selected manuscripts

Filter by year, search by keyword, and copy BibTeX for each listed work.

Projects

Research highlights

A more visual view of methods, artifacts, and active research directions.

CV

Academic timeline

A concise overview of my education, honors, academic service, and professional activities.

Education

Honors

Academic Service

Contact

Open to research conversations and collaboration.

If you are interested in generative model security, uncertainty, or trustworthy AI, feel free to reach out by email.

Expected Ph.D. completion: October 2026. I welcome conversations about postdoctoral and faculty opportunities.