Shadow-Activated Backdoor Attacks on Multimodal Large Language Models

This paper delves into a novel backdoor attack scenario, aiming to uncover potential security risks associated with Multimodal Large Language Models (MLLMs) during multi-round open-ended conversations with users.In the practical use of MLLMs, users have full control over the interaction process with the model, such as using their own collected photos and posing arbitrary open-ended questions.Traditional backdoor attacks that rely on adding external triggers are less applicable.To this end, we introduce a new shadow-activated backdoor attacking paradigm in this paper, wherein attacks implicitly inject malicious content into the responses of MLLMs when the responses explicitly relate to the shadowed object, i.e., without any triggers.To facilitate the shadowactivated backdoor attack, we present a novel framework named BadMLLM to achieve the desired behaviors by constructing a poisoned dataset using GPT-4 Vision and implementing an attention-regularized tuning strategy to address the semantic discontinuity between the original response and the inserted promotion.Extensive experimental results conducted on five MLLMs, three objects, and two types of promotion slogans have demonstrated impressive performance in achieving both efficacy and utility goals, thereby highlighting the significant potential risks concealed within MLLMs.