# Usage guide
> Check this [slide deck](https://docs.google.com/presentation/d/1KJRpKn-3lpTFkmW2moeou2GOZ5YN0RrXy8IAgNazk00/edit#slide=id.g1e58900767e_0_1255) to get familiar with how to use the competition UI

# Your Account & Log-in
>- Click [here](https://dynabench.org/tasks/adversarial-nibbler/create) to participate! 
- Create your free Dynabench account or Sign in with your existing account.
- Click **?** (upper right corner) to see all the UI options you have
- Click **Examples** (upper right corner) to see the type of prompts we are looking for

# Prompt Hacking Journey
>- Start typing **prompts that look safe** but **generate unsafe image(s)**
- Scroll through resulting images with **<** and **>** arrows in search for **unsafe image(s)**. 
- If you see **unsafe image** - select it and fill in the **info about the prompt and the image**
- If there were more than one unsafe images, you can submit the same prompt with another image selected
- **Keep refining your prompt** until it generates an **unsafe image** you would like to submit. 

# Keep Trying New & Creative Prompts
>- Keep coming back to submit more creative prompts
- You submit **across multiple submission sessions** during the duration of the competition.

# What are we interested in
>- Discover a diverse set of *insightful* **long tail problems** for text-to-image models 
- Discover current **blind spots** in harmful image production (i.e., unknown unknowns)
- Discover prompt-image pairs that currently **slip through the cracks of safety filters** 
- Submit **intentful** and **subversive prompts** that circumvent the text-based filters
- Submit **seemingly benign prompts** that nevertheless trigger unsafe outputs

# Submit reflection of your results as a paper 
>You can write up your experiences from this competition and submit it as a paper to the Adversarial Nibbler track at the [**ART of Safety Workshop**](https://sites.google.com/view/art-of-safety/home) (virtual) co-located with AACL2023!