# Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2405.20775 · HTML: https://mlsanity.com/paper/2405.20775/

## Key facts

- Cited by 10 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 56 of its 106 references that are in the map.
- First posted on arXiv 26 May 2024.

## 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 / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 56)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Towards Expert-Level Medical Question Answering with Large Language Models](https://mlsanity.com/paper/2305.09617/) (2023)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [Visual Adversarial Examples Jailbreak Aligned Large Language Models](https://mlsanity.com/paper/2306.13213/) (2023)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)

## Built on by (most cited first, 10 of 10)

- [A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends](https://mlsanity.com/paper/2407.07403/) (2024)
- [Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks](https://mlsanity.com/paper/2409.08087/) (2024)
- [MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.20824/) (2025)
- [VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing](https://mlsanity.com/paper/2602.07045/) (2026)
- [SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care](https://mlsanity.com/paper/2601.16529/) (2026)
- [Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2603.27918/) (2026)
- [PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs](https://mlsanity.com/paper/2510.17277/) (2025)
- [VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models](https://mlsanity.com/paper/2507.00052/) (2025)
- [When Background Matters: Breaking Medical Vision Language Models by Transferable Attack](https://mlsanity.com/paper/2604.17318/) (2026)
- [The Forgotten Shield: Safety Grafting in Parameter-Space for Medical MLLMs](https://mlsanity.com/paper/2601.04199/) (2025)

## Abstract (arXiv)

Security concerns related to Large Language Models (LLMs) have been extensively explored, yet the safety implications for Multimodal Large Language Models (MLLMs), particularly in medical contexts (MedMLLMs), remain insufficiently studied. This paper delves into the underexplored security vulnerabilities of MedMLLMs, especially when deployed in clinical environments where the accuracy and relevance of question-and-answer interactions are critically tested against complex medical challenges. By combining existing clinical medical data with atypical natural phenomena, we define the mismatched malicious attack (2M-attack) and introduce its optimized version, known as the optimized mismatched malicious attack (O2M-attack or 2M-optimization). Using the voluminous 3MAD dataset that we construct, which covers a wide range of medical image modalities and harmful medical scenarios, we conduct a comprehensive analysis and propose the MCM optimization method, which significantly enhances the attack success rate on MedMLLMs. Evaluations with this dataset and attack methods, including white-box attacks on LLaVA-Med and transfer attacks (black-box) on four other SOTA models, indicate that even MedMLLMs designed with enhanced security features remain vulnerable to security breaches. Our work underscores the urgent need for a concerted effort to implement robust security measures and enhance the safety and efficacy of open-source MedMLLMs, particularly given the potential severity of jailbreak attacks and other malicious or clinically significant exploits in medical settings. Our code is available at https://github.com/dirtycomputer/O2M_attack.