MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Xin Liu*, Yichen Zhu, Jindong Gu, Yunshi Lan, Chao Yang, Yu Qiao ;

"redWarning: This paper contains examples of harmful language and images, and reader discretion is recommended. The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models (MLLMs) can be easily compromised by simple query-relevant images when paired with a malicious text query. This attack is achieved without the need for adversarial attacks on either the text or the images. To address this, we introduce MM-SafetyBench, a comprehensive framework designed for conducting safety-critical evaluations of MLLMs against such image-based manipulations. We have compiled a dataset comprising 13 scenarios, resulting in a total of 5,040 text-image pairs. Our analysis across 12 state-of-the-art models reveals that MLLMs are susceptible to breaches instigated by our approach, even when the equipped LLMs have been safety-aligned. In response, we propose a straightforward yet effective prompting strategy to enhance the resilience of MLLMs against these types of attacks. Our work underscores the need for a concerted effort to strengthen and enhance the safety measures of open-source MLLMs against potential malicious exploits. The resource is available at https://github.com/isXinLiu/MM-SafetyBench."