Tutorials: Machine Learning Models, Adversarial Attacks and Defense Strategies

Adversarial attacks can disrupt any AI based system functionalities; while handling such attacks are challenging, but also provide significant research opportunities. The tutorial will cover emerging adversarial machine learning attacks on systems and the state-of-the- art defense techniques. First, we will explore how and where adversarial attacks can happen in an AI framework. We will then present classification of adversarial attacks and their severity and applicability for AI/ML-based security. We will discuss limitations of existing defenses in their implementation. Following that, we will present possible research directions in addressing adversarial learning challenges:

Outline of the tutorial:
Introduction to ML Methods and Adversarial Machine Learning (AML).
Case Studies: AI/ML threats and possible impact on industry.
AML Techniques in different media (image, video and audio) and simulating GAN.
Existing defenses against AML using different computational algorithms.
Challenges and research opportunities in AML defense.

Learning outcomes:
Conceptualize adversarial ML attacks and defenses.
Familiarized with the different computational algorithm that can work in Adversarial MLDomain