# Can Large Language Models Automatically Jailbreak GPT-4V?

arXiv: https://arxiv.org/abs/2407.16686 · HTML: https://mlsanity.com/paper/2407.16686/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [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)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [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)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts](https://mlsanity.com/paper/2311.05608/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [Low-Resource Languages Jailbreak GPT-4](https://mlsanity.com/paper/2310.02446/) (2023)
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://mlsanity.com/paper/2212.08061/) (2022)
- [How Robust is Google's Bard to Adversarial Image Attacks?](https://mlsanity.com/paper/2309.11751/) (2023)
- [Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2401.17263/) (2024)
- [Safety of Multimodal Large Language Models on Images and Texts](https://mlsanity.com/paper/2402.00357/) (2024)
- [Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts](https://mlsanity.com/paper/2311.09127/) (2023)
- [TouchStone: Evaluating Vision-Language Models by Language Models](https://mlsanity.com/paper/2308.16890/) (2023)
- [GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse](https://mlsanity.com/paper/2401.01523/) (2024)
- [Why do universal adversarial attacks work on large language models?: Geometry might be the answer](https://mlsanity.com/paper/2309.00254/) (2023)
- [Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings](https://mlsanity.com/paper/2406.13662/) (2024)

## Built on by (most cited first, 2 of 2)

- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense](https://mlsanity.com/paper/2601.03594/) (2026)

## Abstract (arXiv)

GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite researchers' efforts in safety alignment through RLHF or preprocessing filters, vulnerabilities might still be exploited. In our study, we introduce AutoJailbreak, an innovative automatic jailbreak technique inspired by prompt optimization. We leverage Large Language Models (LLMs) for red-teaming to refine the jailbreak prompt and employ weak-to-strong in-context learning prompts to boost efficiency. Furthermore, we present an effective search method that incorporates early stopping to minimize optimization time and token expenditure. Our experiments demonstrate that AutoJailbreak significantly surpasses conventional methods, achieving an Attack Success Rate (ASR) exceeding 95.3%. This research sheds light on strengthening GPT-4V security, underscoring the potential for LLMs to be exploited in compromising GPT-4V integrity.