WebMirage

WebMirage Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution Wanjing Han, Levi Taiji Li, Mu Zhang, Yue Jiang, Guanhong Tao — University of Utah WebMirage is a red-teaming framework for vision-grounded web agents. It crafts localized adversarial perturbations on...

Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models

The growing misuse of Vision-Language Models VLMs has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against adversarial attacks remains underexplored. We introduce Multi-Faceted...

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models Via Non-Textual Modalities

Existing attacks against multimodal language models MLLMs primarily communicate instructions through text accompanied by adversarial images. In contrast, we exploit the capabilities of MLLMs to interpret non-textual instructions, specifically, adversarial images or audio generated by our novel...