Defending Jailbreak Attack in VLMs via Cross-modality Information Detector
Abstract: Vision Language Models (VLMs) extend the capacity of LLMs to comprehensively understand vision information, achieving remarkable performance in many vision-centric tasks.
Despite that, recent studies have shown that these models are susceptible to jailbreak attacks, which refer to an exploitative technique where malicious users can break the safety alignment of the target model and generate misleading and harmful answers. This potential threat is caused by both the inherent vulnerabilities of LLM and the larger attack scope introduced by vision input.
To enhance the security of VLMs against jailbreak attacks, researchers have developed various defense techniques. However, these methods either require modifications to the model's internal structure or demand significant computational resources during the inference phase. Multimodal information is a double-edged sword. While it increases the risk of attacks, it also provides additional data that can enhance safeguards. Inspired by this, we propose $\underline{\textbf{C}}$ross-modality $\underline{\textbf{I}}$nformation $\underline{\textbf{DE}}$tecto$\underline{\textbf{R}}$ ($\textit{CIDER})$, a plug-and-play jailbreaking detector designed to identify maliciously perturbed image inputs, utilizing the cross-modal similarity between harmful queries and adversarial images.
This simple yet effective cross-modality information detector, $\textit{CIDER}$, is independent of the target VLMs and requires less computation cost. Extensive experimental results demonstrate the effectiveness and efficiency of $\textit{CIDER}$, as well as its transferability to both white-box and black-box VLMs.
Paper Type: Long
Research Area: Language Modeling
Research Area Keywords: security and privacy, red teaming, applications, robustness
Contribution Types: NLP engineering experiment
Languages Studied: English
Submission Number: 4296
Loading