Our tutorial on Practical Adversarial Robustness at CVPR

Hi all.

I am pleased to let you all know that majority of the materials for our CVPR 2021 tutorial Practical Adversarial Robustness in Deep Learning: Problems and Solutions have been released. This tutorial is organized and presented by Pin-Yu Chen (IBM Research) and myself. The focus of this tutorial is not just to survey different attack types but also how to employ them in practice and how to mitigate them with SOTA methods.

A detailed outline of the tutorial can be found on the official website (includes code and slides too):

Our code uses the following libraries extensively:

  • TensorFlow
  • Keras
  • Neural Structured Learning
  • Foolbox

This tutorial will take place today starting from 10 AM ET. We will host a live QnA at 7:30 PM ET. Tutorial videos will be made available on YouTube soon.