Skip to yearly menu bar Skip to main content


Invited Talk
in
Workshop: Workshop on Socially Responsible Machine Learning

Pin-Yu Chen. Adversarial Machine Learning for Good


Abstract:

Adversarial machine learning is often used as a tool to assess the negative impacts and failure modes of a machine learning system. In this talk, I will present model reprogramming, a new paradigm of data-efficiency transfer learning motivated by studying the adversarial robustness of deep learning models.