# Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts

arXiv: https://arxiv.org/abs/2311.09127 · HTML: https://mlsanity.com/paper/2311.09127/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 19 of 19)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [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)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [Pretraining Language Models with Human Preferences](https://mlsanity.com/paper/2302.08582/) (2023)
- [MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots](https://mlsanity.com/paper/2307.08715/) (2023)
- [How Robust is Google's Bard to Adversarial Image Attacks?](https://mlsanity.com/paper/2309.11751/) (2023)
- [Image Hijacks: Adversarial Images can Control Generative Models at Runtime](https://mlsanity.com/paper/2309.00236/) (2023)
- [Effective Prompt Extraction from Language Models](https://mlsanity.com/paper/2307.06865/) (2023)
- [DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents](https://mlsanity.com/paper/2303.17071/) (2023)
- [The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks](https://mlsanity.com/paper/2304.13861/) (2023)
- [Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques](https://mlsanity.com/paper/2310.08101/) (2023)

## Built on by (most cited first, 30 of 65)

- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models](https://mlsanity.com/paper/2311.17600/) (2023)
- [Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models](https://mlsanity.com/paper/2403.09792/) (2024)
- [Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation](https://mlsanity.com/paper/2403.09572/) (2024)
- [A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models](https://mlsanity.com/paper/2402.13457/) (2024)
- [A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends](https://mlsanity.com/paper/2407.07403/) (2024)
- [Red-Teaming for Generative AI: Silver Bullet or Security Theater?](https://mlsanity.com/paper/2401.15897/) (2024)
- [Safety of Multimodal Large Language Models on Images and Texts](https://mlsanity.com/paper/2402.00357/) (2024)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner](https://mlsanity.com/paper/2406.05498/) (2024)
- [VLSBench: Unveiling Visual Leakage in Multimodal Safety](https://mlsanity.com/paper/2411.19939/) (2024)
- [Machine Unlearning in Generative AI: A Survey](https://mlsanity.com/paper/2407.20516/) (2024)
- [Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)](https://mlsanity.com/paper/2407.14937/) (2024)
- [AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models](https://mlsanity.com/paper/2410.05346/) (2024)
- [Core Knowledge Deficits in Multi-Modal Language Models](https://mlsanity.com/paper/2410.10855/) (2024)
- [Advances and Open Challenges in Federated Foundation Models](https://mlsanity.com/paper/2404.15381/) (2024)
- [Distraction is All You Need for Multimodal Large Language Model Jailbreaking](https://mlsanity.com/paper/2502.10794/) (2025)
- [LLMs Meet Multimodal Generation and Editing: A Survey](https://mlsanity.com/paper/2405.19334/) (2024)
- [MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models](https://mlsanity.com/paper/2406.07594/) (2024)
- [Jailbreaking and Mitigation of Vulnerabilities in Large Language Models](https://mlsanity.com/paper/2410.15236/) (2024)
- [HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States](https://mlsanity.com/paper/2502.14744/) (2025)
- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [DoomArena: A framework for Testing AI Agents Against Evolving Security Threats](https://mlsanity.com/paper/2504.14064/) (2025)
- [JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models](https://mlsanity.com/paper/2406.09321/) (2024)
- [Robust Concept Erasure Using Task Vectors](https://mlsanity.com/paper/2404.03631/) (2024)
- [Ranking Manipulation for Conversational Search Engines](https://mlsanity.com/paper/2406.03589/) (2024)
- [Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey](https://mlsanity.com/paper/2410.23687/) (2024)
- [The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense](https://mlsanity.com/paper/2411.08410/) (2024)
- [Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security](https://mlsanity.com/paper/2404.05264/) (2024)
- [Survey of Adversarial Robustness in Multimodal Large Language Models](https://mlsanity.com/paper/2503.13962/) (2025)

## Abstract (arXiv)

Existing work on jailbreak Multimodal Large Language Models (MLLMs) has focused primarily on adversarial examples in model inputs, with less attention to vulnerabilities, especially in model API. To fill the research gap, we carry out the following work: 1) We discover a system prompt leakage vulnerability in GPT-4V. Through carefully designed dialogue, we successfully extract the internal system prompts of GPT-4V. This finding indicates potential exploitable security risks in MLLMs; 2) Based on the acquired system prompts, we propose a novel MLLM jailbreaking attack method termed SASP (Self-Adversarial Attack via System Prompt). By employing GPT-4 as a red teaming tool against itself, we aim to search for potential jailbreak prompts leveraging stolen system prompts. Furthermore, in pursuit of better performance, we also add human modification based on GPT-4's analysis, which further improves the attack success rate to 98.7%; 3) We evaluated the effect of modifying system prompts to defend against jailbreaking attacks. Results show that appropriately designed system prompts can significantly reduce jailbreak success rates. Overall, our work provides new insights into enhancing MLLM security, demonstrating the important role of system prompts in jailbreaking. This finding could be leveraged to greatly facilitate jailbreak success rates while also holding the potential for defending against jailbreaks.