6 papers
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…
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…
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…
UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mapping
Yanjie Li, Kaisheng Liang, Bin Xiao
In recent research, adversarial attacks on person detectors using patches or static 3D model-based texture modifications have struggled with low success rates due to the flexible n…
Improving Transferable Targeted Attacks with Feature Tuning Mixup
Kaisheng Liang, Xuelong Dai, Yanjie Li +2
Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferab…