2 papers
cs.CR2026
BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
Jia Wu, Yu Pan, Junjun Yang +1
Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Althou…
cs.CV2026
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
Lei Zhang, Yu Pan, Bingrong Dai +1
Diffusion Models (DMs) have achieved remarkable success in image generation, yet recent studies reveal their vulnerability to backdoor attacks, where adversaries manipulate outputs…