Home/Model Training/Visual-Adversarial-Examples-Jailbreak-Large-Language-Models
Visual-Adversarial-Examples-Jailbreak-Large-Language-Models logo

Visual-Adversarial-Examples-Jailbreak-Large-Language-Models

Enrichment pending
Unispac/Visual-Adversarial-Examples-Jailbreak-Large-Language-Models

Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models

GraphCanon updated today · GitHub synced today

281
Stars
30
Forks
24
Open issues
3
Watchers
2y
Last push
PythonCreated Jun 13, 2023

Trust & integrity

Full report
Maintenance
Dormant (789d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Personal account
As of today · Source: github_public_v1
Security (OSV)
No lockfile
As of today · Source: none

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models

Capability facts

Languages
python

Source: github.language · Jul 11, 2026

Categories

Tags

README

Installation

We take MiniGPT-4 (13B) as the sandbox to showcase our attacks. The following installation instructions are adapted from the MiniGPT-4 repository.

1. Set up the environment

git clone https://github.com/Unispac/Visual-Adversarial-Examples-Jailbreak-Large-Language-Models.git

cd Visual-Adversarial-Examples-Jailbreak-Large-Language-Models

conda env create -f environment.yml
conda activate minigpt4

2. Prepare the pretrained weights for MiniGPT-4

As we directly inherit the MiniGPT-4 code base, the guide from the MiniGPT-4 repository can also be directly used to get all the weights.

  • Get Vicuna: MiniGPT-4 (13B) is built on the v0 version of Vicuna-13B. Please refer to this guide from the MiniGPT-4 repository to get the weights of Vicuna.

    Then, set the path to the vicuna weight in the model config file here at Line 16.

  • Get MiniGPT-4 (the 13B version) checkpoint: download from here.

    Then, set the path to the pretrained checkpoint in the evaluation config file in eval_configs/minigpt4_eval.yaml at Line 11.