Stanford Webinar with Dan Boneh - Hacking AI: Security & Privacy of Machine Learning Models

In this webinar, Professor Dan Boneh discusses recent work at the intersection of cybersecurity and machine learning. Specifically, he explores an area known as “adversarial machine learning” which looks at the stability of machine learning models in the presence of adversarial behavior.

#artificialintelligence #machinelearning

[rexbriggs]

Outstanding content. Dan, thank you for sharing this. Love the Cat and Guacamole example. It is eye opening and should be required viewing for anyone using AI.

[HimanshuMauryadesigners]

Such wonderful informative content for free us terrific 🔥

[alexkuzmin]

what about side-channel attacks, prof?

[nonindividual]

Half the talk is just examples (I've only watched the first half so far): adversarial examples are already well-known and documented, so I'm not sure if I've learned anything new so far. Pretty frustrating.

Let's see if the second half is any better.