Hola! This is a collection of cool papers, articles and resources for learning about Adversarial attacks. A comprehensive list of articles, research papers, books, videos and other resources is listed below. I hope this will help anyone interested in learning about adversarial attacks.
Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they're like optical illusions for machines. Pretty cool,huh!
Some useful online articles are listed below:
- https://openai.com/blog/adversarial-example-research/
- https://towardsdatascience.com/adversarial-attacks-in-machine-learning-and-how-to-defend-against-them-a2beed95f49c
- https://towardsdatascience.com/breaking-neural-networks-with-adversarial-attacks-f4290a9a45aa
- Wikipedia article on Adversarial attacks
- Adversarial Robustness Toolbox by IBM
- List of published white-box defenses to adversarial examples that have been open-sourced, along with third-party analyses / security evaluations that have been open-sourced
I found these videos pretty useful in learning about Adversarial attacks:
- Siraj Raval's Explanation of Adversial Netoworks
- Ian Goodfellow's lecture on adversarial attacks in Standford Unitersity
- A very cool and short video giving an overview on Adversarial Examples and the "One Pixel attack" by Two Minute Papers
Here are some intersting GitHub Repos:
I'll Keep updating this repo as I learn more and come across more resources on adversarial attacks.