Skip to yearly menu bar Skip to main content


Keynote
in
Affinity Workshop: Muslims in ML

Adversarial Examples Beyond Security

Hadi Salman


Abstract:

Adversarial examples are often perceived as threats that deceive AI models, posing security risks. This talk aims to reframe adversarial examples as beneficial tools, emphasizing their positive impact on AI deployment. Specifically, we will discuss their application in two key areas: designing robust objects and safeguarding against unauthorized AI-based image manipulations. Our discussion will offer a nuanced perspective on the role of adversarial examples in AI.

Chat is not available.