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:
The topics will be covered (2 hours):
- 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.• Expected length of the tutorial: 2h
The level of the tutorial: Introductory
Presenters
Dipankar Dasgupta
Professor of Computer Science at the University of Memphis
Dr. Dipankar Dasgupta is a Professor of Computer Science at the University of Memphis; he completed his Ph.D in 1994 in the area of nature-inspired algorithms for Search and Optimization. His research interests are broadly in the area of scientific computing, design, and development of intelligent solutions inspired by biological processes. His book, “Immunological Computation”, is a graduate level textbook, was published by CRC press in 2009. He also edited two books: one on Evolutionary Algorithms in Engineering Applications (1996) and the other is entitled “Artificial Immune Systems and Their Applications”, published by Springer-Verlag in 2008 . His latest textbook on Advances in User Authentication will be published by Springer- Verlag, 2016.Dr. Dasgupta has more than 300 publications with 18000+ citations and having h-index of 62 as per Google scholar. He received four Best Paper Awards at international conferences (1996, 2006, 2009, and 2012) and two Best Runner-Up Paper Awards (2013 and 2014). Among other awards, he is the recipient of 2012 Willard R. Sparks Eminent Faculty Award, the highest distinction and most prestigious honor given to a faculty member by the University of Memphis. Prof. Dasgupta received the 2014 ACM SIGEVO Impact Award, and also designated as an ACM Distinguished Speaker from 2015-2020.
Kishor Datta Gupta:
Post Doc of at North Carolina A&T University
Kishor Datta Gupta completed his Ph.D. in computer science from the University of Memphis in 2021. He is currently working as a Post-doc scholar at North Carolina A&T University and presently researching Autonomous system vulnerabilities. His research interest includes evolutionary computation, Adversarial machine learning, algorithm bias. He is co-inventor of adversarial defense system patent.