ClementSicard / Reliable-and-Trustworthy-AI-Notebooks

Reliable and Trustworthy Intelligence AI notebooks from ETH Zurich course taught by Prof. Dr. Martin Vechev

Reliable and Trustworthy AI Notebooks

This repository contains the notebooks I worked on in the frame of 263-2400-00L Reliable and Trustworthy Artificial Intelligence taught by Prof. Dr. Martin Vechev.

Contents

• Targeted and untargeted FGSM attacks on pre-trained Neural Networks
• PGD and TRADES defenses for adversarial-attacks-resistant Neural Networks