# Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts

arXiv: https://arxiv.org/abs/2407.15050 · HTML: https://mlsanity.com/paper/2407.15050/

## Key facts

- Cited by 42 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 31 of its 51 references that are in the map.
- First posted on arXiv 21 Jul 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 / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 30 of 31)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Towards Adversarial Attack on Vision-Language Pre-training Models](https://mlsanity.com/paper/2206.09391/) (2022)
- [On the Adversarial Robustness of Vision Transformers](https://mlsanity.com/paper/2103.15670/) (2021)
- [Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures](https://mlsanity.com/paper/2112.05224/) (2021)
- [Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models](https://mlsanity.com/paper/2210.09545/) (2022)
- [Red Teaming Language Model Detectors with Language Models](https://mlsanity.com/paper/2305.19713/) (2023)
- [You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content](https://mlsanity.com/paper/2308.05596/) (2023)
- [Reducing the Vision and Language Bias for Temporal Sentence Grounding](https://mlsanity.com/paper/2207.13457/) (2022)
- [Training-free Lexical Backdoor Attacks on Language Models](https://mlsanity.com/paper/2302.04116/) (2023)
- [IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training](https://mlsanity.com/paper/2207.05333/) (2022)
- [MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning](https://mlsanity.com/paper/2201.12596/) (2022)

## Built on by (most cited first, 30 of 42)

- [LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://mlsanity.com/paper/2502.21321/) (2025)
- [SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types](https://mlsanity.com/paper/2410.21965/) (2024)
- [Visual Prompting in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2409.15310/) (2024)
- [IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves](https://mlsanity.com/paper/2411.00827/) (2024)
- [Distraction is All You Need for Multimodal Large Language Model Jailbreaking](https://mlsanity.com/paper/2502.10794/) (2025)
- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization](https://mlsanity.com/paper/2412.05892/) (2024)
- [Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard](https://mlsanity.com/paper/2511.10222/) (2025)
- [Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study](https://mlsanity.com/paper/2505.15389/) (2025)
- [JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering](https://mlsanity.com/paper/2508.05087/) (2025)
- [Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models](https://mlsanity.com/paper/2411.11496/) (2024)
- [Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations](https://mlsanity.com/paper/2410.09097/) (2024)
- [Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models](https://mlsanity.com/paper/2505.16446/) (2025)
- [REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM](https://mlsanity.com/paper/2505.04673/) (2025)
- [SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses](https://mlsanity.com/paper/2510.15476/) (2025)
- [Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures](https://mlsanity.com/paper/2502.17710/) (2025)
- [GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models](https://mlsanity.com/paper/2506.10047/) (2025)
- [CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks](https://mlsanity.com/paper/2510.17687/) (2025)
- [JPRO: Automated Multimodal Jailbreaking via Multi-Agent Collaboration Framework](https://mlsanity.com/paper/2511.07315/) (2025)
- [Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs](https://mlsanity.com/paper/2601.06460/) (2026)
- [Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2603.27918/) (2026)
- [Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap](https://mlsanity.com/paper/2505.24208/) (2025)
- [Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions](https://mlsanity.com/paper/2509.25539/) (2025)
- [TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration](https://mlsanity.com/paper/2603.22882/) (2026)
- [LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models](https://mlsanity.com/paper/2604.18803/) (2026)
- [Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs](https://mlsanity.com/paper/2505.14226/) (2025)
- [Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation](https://mlsanity.com/paper/2507.11968/) (2025)
- [Resource Consumption Red-Teaming for Large Vision-Language Models](https://mlsanity.com/paper/2507.18053/) (2025)
- [JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation](https://mlsanity.com/paper/2509.21401/) (2025)
- [Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation](https://mlsanity.com/paper/2511.19257/) (2025)

## Abstract (arXiv)

Large Vision Language Models (VLMs) extend and enhance the perceptual abilities of Large Language Models (LLMs). Despite offering new possibilities for LLM applications, these advancements raise significant security and ethical concerns, particularly regarding the generation of harmful content. While LLMs have undergone extensive security evaluations with the aid of red teaming frameworks, VLMs currently lack a well-developed one. To fill this gap, we introduce Arondight, a standardized red team framework tailored specifically for VLMs. Arondight is dedicated to resolving issues related to the absence of visual modality and inadequate diversity encountered when transitioning existing red teaming methodologies from LLMs to VLMs. Our framework features an automated multi-modal jailbreak attack, wherein visual jailbreak prompts are produced by a red team VLM, and textual prompts are generated by a red team LLM guided by a reinforcement learning agent. To enhance the comprehensiveness of VLM security evaluation, we integrate entropy bonuses and novelty reward metrics. These elements incentivize the RL agent to guide the red team LLM in creating a wider array of diverse and previously unseen test cases. Our evaluation of ten cutting-edge VLMs exposes significant security vulnerabilities, particularly in generating toxic images and aligning multi-modal prompts. In particular, our Arondight achieves an average attack success rate of 84.5% on GPT-4 in all fourteen prohibited scenarios defined by OpenAI in terms of generating toxic text. For a clearer comparison, we also categorize existing VLMs based on their safety levels and provide corresponding reinforcement recommendations. Our multimodal prompt dataset and red team code will be released after ethics committee approval. CONTENT WARNING: THIS PAPER CONTAINS HARMFUL MODEL RESPONSES.