9 papers
Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions
Neha Nagaraja, Lan Zhang, Zhilong Wang +2
Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection…
ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection
Ruize Ma, Minghong Cai, Yilei Jiang +7
Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced…
Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarks
Wenkai Fu, Finn Carter, Yue Wang +2
Robust invisible watermarking aims to embed hidden messages into images such that they survive various manipulations while remaining imperceptible. However, powerful diffusion-base…
Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
Yi Xin, Qi Qin, Siqi Luo +29
We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by util…
Diffusion-Based Image Editing for Breaking Robust Watermarks
Yunyi Ni, Finn Carter, Ze Niu +2
Robust invisible watermarking aims to embed hidden information into images such that the watermark can survive various image manipulations. However, the rise of powerful diffusion-…
Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustness
Zixuan Fu, Yan Ren, Finn Carter +5
Diffusion models have achieved unprecedented success in image generation but pose increasing risks in terms of privacy, fairness, and security. A growing demand exists to \emph{era…