Date: 27 September 2023
Time: 10:30 AM ET (New York Time)
Speaker(s): Dr. Nhien-An Le-Khac, Dr. Aditya Kuppa
Original Article (Free to download - open access)
Machine learning methods are essential in addressing cybersecurity threats and explaining the decision process of black-box classifiers is critical to their successful adoption. Counterfactual explanations have emerged as a popular approach to understanding why black-box models make confident decisions and highlight alternative data instances that could change the outcomes. However, recent research in Explainable Artificial Intelligence (XAI) has focused on improving explain ability methods, attacks on interpreters, and defining properties of model explanations, overlooking the potential introduction of new attack surfaces through explanations. Adversaries can exploit explanations to launch attacks, compromising system privacy and integrity. Understanding these risks is crucial and developing strategies to mitigate threats is necessary to ensure the security of AI systems.
In this webinar, we will explore cybersecurity properties and threat models associated with counterfactual explanations. We will delve into new black-box attacks that exploit Explainable Artificial Intelligence (XAI) methods, compromising the confidentiality and privacy of underlying classifiers. Additionally, we will discuss the significance of these attacks within the context of Large Language Models.
Dr. Nhien-An Le-Khac obtained the PhD. in Computer Science in 2006 at the Institute National Polytechnique Grenoble (INPG), France. His research interest spans the area of Cybersecurity and Digital Forensics, Machine Learning for Security, Fraud and Criminal Detection, Cloud Security and Privacy, High Performance computing and Secure Healthcare IT systems.
He is an Associate Professor at the School of Computer Science (CS), UCD and is currently the Program Director of MSc program in Forensic Computing and Cybercrime Investigation - an international program for the law enforcement officers specializing in cybercrime investigations. He is also the co-founder of UCD-GNECB Postgraduate Certificate in fraud and e-crime investigation. He was a Research Fellow in Citibank, Ireland (Citi). Since 2013, he has collaborated on many research projects as a principal/co-PI/funded investigator.
Dr. Le-Khac successfully supervised multiple PhD students and published 3 books and more than 200 scientific papers in peer-reviewed journals and conferences in related research fields. He is an associate editor of Elsevier IoT journals and an active chair as well as a reviewer for many key conferences and journals in related disciplines.
Dr. Aditya Kuppa completed the Ph.D. in Computer Science at University College Dublin in 2022.
He has a background in the cybersecurity industry spanning two decades and has held various roles and contributed significantly to the field.
Dr. Kuppa has published scientific papers in esteemed peer-reviewed conferences and holds 15 patents related to cybersecurity. Additionally, he actively participates in the community as a reviewer for numerous important conferences and journals in related disciplines.