MAI-2025-0008

Multimodal Large Language Models MLLMs are susceptible to a sophisticated attack vector that exploits narrative-driven visual storytelling and role immersion to bypass inherent safety protocols. This attack, known as MIRAGE, strategically decomposes malicious queries into triplets consisting of...

MAI-2024-0010

Multimodal Large Language Models MLLMs are susceptible to a heuristic-induced multimodal risk distribution jailbreak attack. This sophisticated attack method effectively bypasses existing safety mechanisms by dispersing malicious prompts across both text and image modalities. This distribution...

MAI-2025-0007

Multimodal Large Language Models MLLMs are susceptible to attacks based on Jailbreak Probability, known as Jailbreak-Probability-based Attacks JPA. These attacks utilize a specialized Jailbreak Probability Prediction Network JPPN to detect and refine adversarial perturbations within input images...

MAI-2024-0056

This vulnerability pertains to multimodal large language models MLLMs, where attackers can efficiently perform jailbreaking attacks by utilizing visual inputs to circumvent established safety protocols. The attack methodology involves integrating a visual module into the target LLM, followed by...

MAI-2024-0059

Multimodal Large Language Models MLLMs operating within multi-agent environments are susceptible to a sophisticated attack known as "infectious jailbreak." This vulnerability is triggered by the introduction of a single adversarial image into the memory of one agent, which can rapidly propagate...

MAI-2023-0004

Multimodal Large Language Models MLLMs are susceptible to a newly identified attack vector involving query-relevant images. These images, crafted using advanced techniques such as Stable Diffusion and typography, can circumvent established safety protocols and provoke unsafe outputs, even when th...