Speaker: Dr. Murat Kantarcioglu
From: The University of Texas at Dallas
Abstract
In the age of big data and Artificial Intelligence (AI), protecting the security and privacy of stored data is paramount for maintaining public trust, accountability and getting the full value from the collected data. Therefore, we need to address security and privacy challenges ranging from allowing access to big data to building fair AI models using the privacy sensitive data. In this talk, I provide an overview of our end-to-end solution framework that addresses these security and privacy challenges that arise in the age of AI. In addition, I discuss our federated learning framework that is designed to be robust against poisoning attacks and when humans can work with AI to improve decision outcomes and fairness. Finally, we discuss our work on improving the fairness of AI models using synthetic data and data modification.
For more info, please follow this link.
Read More