About
I am a Ph.D. at Nanjing University of Aeronautics and Astronautics (NUAA), 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 (IEEE/ACM Fellow).
Email: xukun930@nuaa.edu.cn; xukun930@gmail.com; xukun12138@outlook.com
If you are interested in my research, feel free to reach out by email.
Research Interests: Generative Model Security, Uncertainty, Trustworthy AI
Topic: generative concept, uncertainty analysis, causal analysis, personalized/customized text-image (T2I) generation, content toxicity detection, diffusion model, foundation model
My OpenReview and ORCID homepage.
News
- 🎉 [Apr 2026] A research work manuscript on malicious concept detection has been accepted by IEEE TDSC.
- 🔥 [Apr 2026] A research work manuscript on concept-level risk and calibration has been submitted for peer review.
- 🔥 [Feb 2026] A research work manuscript on uncertainty in concept-driven diffusion model has been submitted for peer review.
- 🔥 [Jan 2026] A research work manuscript on deepfake detection has been submitted for peer review.
- 📅 [Nov 2025] A talk with Prof. Pierangela Samarati (IEEE/ACM Fellow) and Prof. Vincenzo Piuri (IEEE Fellow) at the Università degli Studi di Milano.
- 📅 [Oct 2025] A minisymposium "Generative Concept Security in Trustworthy AIGC" at the Università degli Studi dell'Insubria [slides].
- 🎉 [Jul 2025] I am honored to be awarded the CSC Excellence Talent Program Scholarship [letter].
Publications
(* indicates the corresponding author. Full list of publications)
Journal Articles
-
🔥 [2026 TDSC] Detecting Malicious Concepts Without Image Generation in AI-Generated Content (AIGC)
Kun Xu, Wenying Wen, Shuren Qi, Tao Wang, Yushu Zhang*, Yuming Fang.
IEEE Transactions on Dependable and Secure Computing (CCF A) -
📑 [2025 Arxiv] Make Identity Unextractable yet Perceptible: Synthesis-Based Privacy Protection for Subject Faces in Photos
Tao Wang, Yushu Zhang, Xiangli Xiao, Kun Xu, Lin Yuan, Wenying Wen, Yuming Fang.
Arxiv -
📑 [2025 JCES] A Facial Manipulation Adversarial Defense Approach for Image Post-Processing
Kun Xu, Shuren Qi, Yushu Zhang*, Wenying Wen, Hua Zhang.
Computer Engineering & Science -
📑 [2023 MTAP] Facial depth forgery detection based on image gradient
Kun Xu, Gaoming Yang*, Xianjin Fang, Ji Zhang.
Multimedia Tools and Applications -
📑 [2023 TVCJ] Video face forgery detection via facial motion-assisted capturing dense optical flow truncation
Gaoming Yang, Kun Xu*, Xianjin Fang, Ji Zhang.
The Visual Computer
Honors
- 🎖 Excellence Talent Program Scholarship China Scholarship Council (CSC) Jul. 2025
- 🎖 Outstanding Graduates Anhui Provincial Department of Education Jun. 2023