5 papers
StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
Yanjie Li, Wenxuan Zhang, Xinqi Lyu +2
Recently, text-to-image diffusion models have been widely used for style mimicry and personalized customization through methods such as DreamBooth and Textual Inversion. This has r…
AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
Yanjie Li, Yiming Cao, Dong Wang +1
Multimodal agents built on large vision-language models (LVLMs) are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection, especially throug…
Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
Yiming Cao, Yanjie Li, Kaisheng Liang +1
The growing deployment of Large Vision-Language Models (VLMs) raises safety concerns, as adversaries may exploit model vulnerabilities to induce harmful outputs, with targeted blac…
Beyond the Visible: Benchmarking Occlusion Perception in Multimodal Large Language Models
Zhaochen Liu, Kaiwen Gao, Shuyi Liang +4
Occlusion perception, a critical foundation for human-level spatial understanding, embodies the challenge of integrating visual recognition and reasoning. Though multimodal large l…
PLA: Prompt Learning Attack against Text-to-Image Generative Models
Xinqi Lyu, Yihao Liu, Yanjie Li +1
Text-to-Image (T2I) models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generatin…