# LLaVAGuard


PyTorch implementation for the paper "*[LLaVAGuard: Safety Guardrails for Multimodal Large Language Models against Jailbreak Attacks](#)*"

LLaVAGuard is a novel framework that offers multimodal safety guardrails to any input prompt. The safety guardrails are specifically optimized to minimize the likelihood of generating harmful responses on LLaVA-v1.5 model. We have also demonstrated  the transferability of these guardrails to other prominent MLLMs, including GPT-4V, MiniGPT-4, and InstructBLIP, thereby broadening the scope of our solution. 

## Project Structure


- **`cal_metrics.py`:** Summarizing the perplexity metrics over all examples
- **`get_metric.py`**: Script for calculating detoxify and Perspective API metrics.
- **`eval_configs`:** Configuration files for model evaluations, including settings for llama and MiniGPT-4.
- **`image_safety_patch.py`, `text_safety_patch.py`:** Scripts for generating safety patches from images and text.
- **`instructblip_*.py`:** Scripts related to the InstructBLIP model, including defense strategies against constrained and unconstrained attacks, and question answering.
- **`lavis`:** Submodule for the InstructBLIP model, which contains the dataset builders, models, processors, projects, runners, and tasks for various multimodal learning purposes.
- **`metric`:** Implementations of metrics such as detoxify and Perspective API.
- **`minigpt_*.py`:** Scripts related to the MiniGPT-4 model, including constrained and unconstrained inference, and question answering.
- **`requirements.txt`:** Required Python packages for setting up the project.
- **`scripts`:** Shell scripts for running all experiments. 
- **`utils.py`:** Utility functions supporting various operations across the project, such as image loading and preprocessing. 
- **`visual`:** Scripts for visualizing the overall toxicity results from InstructBLIP and MiniGPT-4 evaluations.
- **`text_patch_heuristic`**: pre-defined text guardrails
- **`text_patch_optimized`**: optimized text guardrails

## Setup

To get started with llavaguard, follow these setup steps:

1. **Clone the Repository:**
   ```bash
   git clone <repository-url> llavaguard
   cd llavaguard
   ```

2. **Install Dependencies:**
   Make sure you have Python 3.10+ installed, then run:
   ```bash
   pip install -r requirements.txt
   ```

3. **Dataset Preparation:**
   Download the two files from [Google Drive](https://drive.google.com/drive/folders/14vdgC4L-Je6egzmVOfVczQ3-j-IzBQio?usp=sharing) and put them under the project directory. Run:
   
   ```bash
   tar -xzvf adversarial_qna_images.tar.gz
   tar -xzvf unconstrained_attack_images.tar.gz
   ```


## Usage

The project includes several scripts and shell commands designed to perform specific tasks. Here are some examples:


- Running constrained / unconstrained attack as well as the QNA task for the InstructBLIP model:
  ```bash
  bash scripts/run_instructblip_attack.sh
  ```
  
  This involves getting the results from the LLMs and calculating the metrics.

  Procedures to run MiniGPT-4 are similar.

- Running experiments for the baseline defense methods:
  ```bash
  bash scripts/run_instructblip_baseline.sh
  ```
  
- Running our LLaVAGuard defense methods:
    ```bash
  bash scripts/run_instructblip_safety_patch.sh
  ```

## Contributing

Contributions to llavaguard are welcomed. Please submit pull requests to the repository with a clear description of the changes and the purpose behind them.

## License

This project is released under the Apache 2.0 License.