smasis001 / odsc-east-2022

Workshop for Open Data Science Conference East 2022

Workshop for Open Data Science Conference East 2022

Adversarial Robustness: How to make Artificial Intelligence models attack-proof!

Downloadable Pre-requisites

• Jupyter environment with *Python >= 3.6 and the following python libraries are required:

1. *Matplotlib >= 3.1.3 ( 20M)
2. *Scikit Learn >= 0.22.1 ( 27M)
3. *Numpy >= 1.18.1 ( 22M)
4. *Seaborn >= 0.10.0 ( 1.8M)
5. *Tensorflow>=2.4.1 ( 65M)
6. *Tqdm>=4.41.1 ( 1.7M)
7. adversarial-robustness-toolbox>1.5.0 ( 3.2M)
8. machine-learning-datasets>=0.01.16 ( 0.3M)

(please note that Google Colab comes with all those marked with * pre-installed and code provided will come with instructions on how to install everything else)

Dataset located here: https://github.com/PacktPublishing/Interpretable-Machine-Learning-with-Python/raw/master/datasets/maskedface-net_thumbs_sampled.zip (349.4M)

Additional Instructions

If you plan to run workshops code in your local machine, make sure you have a working Jupyter environment with the latest version of Python. If you don’t have one, you can install Anaconda, but please do so before the session. The code we will using is located here: part 1, part 2. Although additional libraries can be installed quickly and usually do so without any issues, it is recommended that you install them in advance (just in case the local environment presents some problems).

If you are planning to run the code in the cloud, the Colab notebook is located here: part 1, part 2. It will come with instructions on how to install the additional libraries in Colab. Please install these at the beginning of the session.