Adversarial Attacks

Abstract

SecureAI is a cybersecurity and privacy training program designed for AI professionals and researchers to equip them with the knowledge and skills to build AI systems that are technically sound and secure. In this talk I provide an introduction to adversarial examples and guidelines for robustness evaluations in practical systems.

Date
May 29, 2024
Location
Loyola University Chicago in Chicago, IL
Blaine Hoak
Blaine Hoak
Ph.D. Student in Computer Sciences

Researching Trustworthy AI.