Help Henry Hacker stop the robot uprising -- Brought to you by the [AI Village](https://aivillage.org/)! In this series of challenges, you'll be interacting with various machine learning security challenges.

The competition will be live from January 27th to January 30th @ 12:00. If you're at CactusCon, stop by the village to chat about the competition. There's also the Kaggle Discussion Board, but that will only be periodically monitored.

## Quickstart
Look at the `template.ipynb` notebook in the competition data and follow the instructions.

## Process
This capture-the-flag (CTF) follows a different flow than most Kaggle competitions. Competitors will be interacting with API endpoints or code/objects stored in the `input `directory during each of the challenges. Upon successful completion of a challenge, that challenge will return a flag (unique-to-you strings with a length of 128 characters). To update the scoreboard, competitors will submit a `.csv` containing all of their flags -- see [the Kaggle documentation](https://www.kaggle.com/docs/competitions#submitting-by-uploading-a-file) or contact the competition organizers for help. Cumulative scores will be weighted based on the difficulty of the challenge. All competitors start at `0` and work their way towards a perfect score of `1.0`. There are 11 challenges, ensure your `submission.csv` has exactly those 11 challenge rows.

NOTE: The template notebook is just a convenience function and method for submitting flags to the scoreboard. Don't feel constrained to that single operating environment. Interact with the challenges from your local host or any other machine that can access the internet. Afterwards, you can transport your flags into the notebook to update the scoreboard.

NOTE: If you want to interact with online challenges through Kaggle (using the template notebook, for instance), you may need to verify your Kaggle account using a phone number.

Please do not try and hack any infrastructure or share flags. 


## Challenges
CTF's are inherently puzzles that are intended to challenge you and help you learn new things. Sometimes they may be a little ambiguous or misleading. That's part of the challenge!

**Math Challenges:** Four challenges to explore the concept of dimensionality.
**Chatterbot:** Can AI think for itself? 
**Hotdog and Hotterdog:** Dogs, wieners, and classifiers. What more could you want?
**bad2good:** Can you poison a dataset to change how something is classified?
**salt:** This model has some pretty advanced defenses. Can you evade it anyway?
**theft:** Can you steal this model to get a sneaky owl past it?
**inference:** I think something's backwards here. Can you, like, back something out?