3 papers
cs.MM2026
Concept-Level Risk and Calibration for Governance in Diffusion Foundation Models
Kun Xu, Yushu Zhang, Tao Wang +4
Diffusion models have become a core paradigm for multimedia generation, offering powerful concept-driven controllability for personalization, semantic editing, and selective unlear…
cs.CR2025
Make Identity Unextractable yet Perceptible: Synthesis-Based Privacy Protection for Subject Faces in Photos
Tao Wang, Yushu Zhang, Xiangli Xiao +4
Deep learning-based face recognition (FR) technology exacerbates privacy concerns in photo sharing. In response, the research community developed a suite of anti-FR methods to bloc…
cs.CR2025
Detecting Malicious Concepts without Image Generation in AI-Generated Content (AIGC)
Kun Xu, Wenying Wen, Shuren Qi +3
The task of text-to-image generation has achieved tremendous success in practice, with emerging concept generation models capable of producing highly personalized and customized co…