Adversarial Machine Learning and Defense Strategies

[CFAR Distinguished Professor Lecture Series]
Adversarial Machine Learning and Defense Strategies (Hybrid event) by Professor Dipankar Dasgupta 
8 Dec 2022 | 3.00pm (Singapore Time)

Adversarial attacks can disrupt artificial intelligence (AI) and machine learning (ML) based system functionalities but also provide significant research opportunities. In this talk, Prof Dipankar Dasgupta from The University of Memphis will cover emerging adversarial machine learning (AML) attacks on systems and the state-of-the-art defense techniques. Prof Dasgupta will first discuss how and where adversarial attacks could happen in an AI/ML model and framework. He will then present the classification of adversarial attacks and their severity and applicability in real-world problems, including the steps to mitigate their effects, before illustrating the role of GAN in adversarial attacks and as a defence strategy.

Finally, Prof Dasgupta will also discuss a dual-filtering (DF) strategy that could mitigate adaptive or advanced adversarial manipulations for a wide-range of ML attacks with higher accuracy. The developed DF software could be used as a wrapper to any existing ML-based decision support system to prevent a wide variety of adversarial evasion attacks. The DF framework utilises two set of filters based on positive (input filters) and negative (output filters) verification strategies that could communicate with each other for higher robustness.

SPEAKER
talks--Dipankar Dasgupta
Prof Dipankar Dasgupta 
William Hill Professor of Computer Science
Director, Center for Information Assurance (CfIA)
Director, Intelligent Security Systems Research Laboratory
The University of Memphis

Prof Dipankar Dasgupta is a Professor of Computer Science at the University of Memphis. In 1994, he completed his Ph.D in the area of nature-inspired algorithms for Search and Optimisation. His research interests are broadly in the area of scientific computing, design, and development of intelligent solutions inspired by biological processes. Besides being the author of “Immunological Computation”, a graduate level textbook, which was published by CRC press in 2009, Prof Dasgupta also edited two books: “Evolutionary Algorithms in Engineering Applications” in (1996) and "Artificial Immune Systems and Their Applications", which was published by Springer-Verlag in 2008. His latest textbook on Advances in User Authentication was published by Springer-Verlag in 2016.

Prof Dasgupta has more than 300 publications with 19000+ citations and has a h-index of 64 according to 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 also the recipient of the 2012 Willard R. Sparks Eminent Faculty Award, the highest distinction and most prestigious honour given to a faculty member by the University of Memphis. In addition, Prof. Dasgupta was a recipient of the 2014 ACM SIGEVO Impact Award and was designated as an ACM Distinguished Speaker from 2015 - 2020. Currently, he is an IEEE Distinguished Lecturer until 2024.