3 papers
cs.CV2026
Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
Jun Li, Lizhi Xiong, Ziqiang Li +4
Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in larg…
cs.CR2026
Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
Zida Li, Jun Li, Yuzhe Sha +3
Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor sec…
cs.CV2025
Is Artificial Intelligence Generated Image Detection a Solved Problem?
Ziqiang Li, Jiazhen Yan, Ziwen He +4
The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinfo…