4 papers
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…
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…
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
Mengyao Du, Han Fang, Haokai Ma +4
Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious i…
Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models
Jiahao Chen, Yu Pan, Yi Du +2
Recently, the diffusion model has gained significant attention as one of the most successful image generation models, which can generate high-quality images by iteratively sampling…