Machine Learning is itself just another tool, susceptible to adversarial attacks. These can have huge implications, especially in a world with self-driving cars and other automation. In this talk, we will look at recent developments in the world of adversarial attacks on the A.I. systems, and how far we have come in mitigating these attacks.
Introduction to different types of Adversarial Attacks in AI, Confidentiality, Integrity, Availability Attacks
Quick demos and examples of these types of attacks, and where the state of the art is
Defenses against some of these attacks: Adversarial Training, Defensive Distillation
What is next in this field
Co-Founder at Commonlounge