mlsanityData to 7 Oct 2026

FENCE: A Financial and Multimodal Jailbreak Detection Dataset

arXiv 2602.18154 ↗First posted 20 Feb 2026cs.CL cs.AI cs.DBcited by 0

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

also in 1 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 20 of its 33 references that are in the map. First posted on arXiv 20 Feb 2026.

Builds on

20 of 33 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations15 Nov
  2. 2024BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks28 Oct
  3. 2024Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models31 Jul
  4. 2024JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks3 Apr
  5. 2023FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts9 Nov
  6. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models26 Jul

Other references · 14

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  3. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
  4. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  5. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  6. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 478
  7. 2024PaliGemma 2: A Family of Versatile VLMs for Transfercited by 204
  8. 2023Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulationcited by 202
  9. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 189
  10. 2021Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Datacited by 55
  11. 2023JailGuard: A Universal Detection Framework for LLM Prompt-based Attackscited by 46
  12. 2024Perception-guided Jailbreak against Text-to-Image Modelscited by 37
2 more
  1. 2024HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Modelscited by 17
  2. 2024Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense Perspectivecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model
  2. 2025Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models
  3. 2025Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models
  4. 2026Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
  5. 2025Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application
  6. 2026Recursive language models for jailbreak detection: a procedural defense for tool-augmented agents
  7. 2024Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models
  8. 2025Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models