# Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack

arXiv: https://arxiv.org/abs/2505.21967 · HTML: https://mlsanity.com/paper/2505.21967/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models](https://mlsanity.com/paper/2308.01263/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts](https://mlsanity.com/paper/2311.05608/) (2023)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [Visual Adversarial Examples Jailbreak Aligned Large Language Models](https://mlsanity.com/paper/2306.13213/) (2023)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models](https://mlsanity.com/paper/2311.17600/) (2023)
- [Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models](https://mlsanity.com/paper/2307.14539/) (2023)
- [JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2404.03027/) (2024)
- [Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models](https://mlsanity.com/paper/2403.09792/) (2024)
- [AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting](https://mlsanity.com/paper/2403.09513/) (2024)
- [Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation](https://mlsanity.com/paper/2403.09572/) (2024)
- [Towards Interpreting Visual Information Processing in Vision-Language Models](https://mlsanity.com/paper/2410.07149/) (2024)
- [Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations](https://mlsanity.com/paper/2410.02762/) (2024)
- [ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time](https://mlsanity.com/paper/2410.06625/) (2024)
- [Multimodal Situational Safety](https://mlsanity.com/paper/2410.06172/) (2024)
- [Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model](https://mlsanity.com/paper/2406.15279/) (2024)
- [BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks](https://mlsanity.com/paper/2410.20971/) (2024)
- [Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors](https://mlsanity.com/paper/2405.10529/) (2024)
- [Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models](https://mlsanity.com/paper/2501.18533/) (2025)
- [The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense](https://mlsanity.com/paper/2411.08410/) (2024)
- [ELITE: Enhanced Language-Image Toxicity Evaluation for Safety](https://mlsanity.com/paper/2502.04757/) (2025)

## Built on by (most cited first, 5 of 5)

- [SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs](https://mlsanity.com/paper/2510.13190/) (2025)
- [Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?](https://mlsanity.com/paper/2511.20710/) (2025)
- [Agentic Moderation: Multi-Agent Design for Safer Vision-Language Models](https://mlsanity.com/paper/2510.25179/) (2025)
- [Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization](https://mlsanity.com/paper/2605.10764/) (2026)
- [The Uncontrolled Variable: Vision-Language Model Refusal Responds to Image Presence in Ways Risk Cannot Explain](https://mlsanity.com/paper/2609.26174/) (2026)

## Abstract (arXiv)

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security vulnerabilities. In this work, we conduct a systematic representational analysis to uncover why conventional adversarial attacks can circumvent the safety mechanisms embedded in LVLMs. We further propose a novel two stage evaluation framework for adversarial attacks on LVLMs. The first stage differentiates among instruction non compliance, outright refusal, and successful adversarial exploitation. The second stage quantifies the degree to which the model's output fulfills the harmful intent of the adversarial prompt, while categorizing refusal behavior into direct refusals, soft refusals, and partial refusals that remain inadvertently helpful. Finally, we introduce a normative schema that defines idealized model behavior when confronted with harmful prompts, offering a principled target for safety alignment in multimodal systems.