Dr. Safwan Wshah is an Associate Professor of Computer Science at the University of Vermont, where he leads the Vermont Artificial Intelligence Lab (VaiL). His research is dedicated to advancing machine learning theory and its diverse applications, particularly in vision-based glocalization, where we aim to estimate GPS coordinates solely from visual information. his work spans critical areas like healthcare, education, and transportation, with extensive publications in top-tier conferences and journals. He has mentored numerous Ph.D. and Master’s students and secured substantial research funding from major agencies like NSF and NIH. Recently, He was honored with the prestigious Fulbright Global Scholar award to expand my research in ML and satellite imaging. 

As Artificial Intelligence (AI) systems become increasingly integrated into critical applications, from healthcare and finance to autonomous vehicles and cybersecurity but their vulnerabilities to adversarial attacks pose significant risks. This talk will explore the security challenges in AI, specifically focusing on adversarial threats. In this talk, we will cover various topics, including the types of adversarial attacks that can exploit AI models, the techniques used by attackers to compromise AI systems, and the strategies available for defending against these attacks. Through real-world case studies, the presentation will illustrate the potential consequences of adversarial vulnerabilities. Attendees will learn about new research and tools that help make AI systems more secure and reliable as AI becomes a part of our daily lives and critical systems.