FENCE: A Financial and Multimodal Jailbreak Detection Dataset
This addresses the problem of jailbreak risks in financial AI systems, providing a domain-specific dataset for detection, but it is incremental as it focuses on a new dataset rather than a novel detection method.
The authors tackled the lack of resources for jailbreak detection in finance by creating FENCE, a bilingual multimodal dataset, and found that commercial and open-source VLMs show vulnerabilities, with a baseline detector achieving 99% in-distribution accuracy.
Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs). VLMs are particularly vulnerable because they process both text and images, creating broader attack surfaces. However, available resources for jailbreak detection are scarce, particularly in finance. To address this gap, we present FENCE, a bilingual (Korean-English) multimodal dataset for training and evaluating jailbreak detectors in financial applications. FENCE emphasizes domain realism through finance-relevant queries paired with image-grounded threats. Experiments with commercial and open-source VLMs reveal consistent vulnerabilities, with GPT-4o showing measurable attack success rates and open-source models displaying greater exposure. A baseline detector trained on FENCE achieves 99 percent in-distribution accuracy and maintains strong performance on external benchmarks, underscoring the dataset's robustness for training reliable detection models. FENCE provides a focused resource for advancing multimodal jailbreak detection in finance and for supporting safer, more reliable AI systems in sensitive domains. Warning: This paper includes example data that may be offensive.