Saif Eddin Jabari — Investigating Vulnerabilities in Autonomous Vehicle Perception Algorithms
The Center for Urban Science + Progress (CUSP) at NYU Tandon welcome you to attend the lecture "Investigating Vulnerabilities in Autonomous Vehicle Perception Algorithms" by Saif Eddin Jabari, Associate Professor of Civil and Urban Engineering at New York University Abu Dhabi and Global Network Associate Professor at the NYU Tandon School of Engineering, as part of the Spring 2025 Urban Science Research Seminar Series.
About the Lecture
Investigating Vulnerabilities in Autonomous Vehicle Perception Algorithms
Autonomous vehicles (AVs) rely on deep neural networks (DNNs) for critical tasks, such as environment perception—identifying traffic signs, pedestrians, and lane markings—and executing control decisions, including braking, acceleration, and lane changing. However, DNNs are vulnerable to adversarial attacks, including structured perturbations to inputs and misleading training samples that can degrade performance. This presentation begins with an overview of adversarial training, highlighting the impact of input sizes on the vulnerability of DNNs to cyberattacks. Subsequently, I will share our recent findings that explore the hypothesis that DNNs learn approximately linear relationships between inputs and outputs. This conjecture is crucial for developing both adversarial attacks and defense strategies in machine learning security. The final part of the presentation will focus on recent work utilizing error-correcting codes to safeguard DNN-based classifiers.
About the Speaker
Dr. Saif Jabari is an Associate Professor of Civil and Urban Engineering at New York University Abu Dhabi (NYUAD) and a Global Network Associate Professor at the Tandon School of Engineering at NYU in Brooklyn, NY. At NYUAD, he is co-PI of the Center for Integrated Urban Networks (CITIES) and the Center for Stability, Instability, and Turbulence (SITE). He is an Associate Editor for Transportation Science and Area Editor with the new Elsevier journal Artificial Intelligence for Transportation. His research focuses on developing advanced computational methods and theoretical guarantees of performance for urban traffic management problems. The techniques integrate high-resolution traffic data with principles of traffic physics to address the rapidly evolving needs of the field. His current research focuses on understanding and addressing vulnerabilities in deep neural networks, specifically as they relate to environment perception in autonomous vehicles.
Visitor Information
This event will take place at 370 Jay St. Please visit the NYU Tandon website for directions and a campus map. Advance registration through Eventbriteis required for campus access at NYU for external guests.
About the Urban Science Research Seminar Series
The Center for Urban Science + Progress’s annual Research Seminar series features leading voices in the growing field of urban informatics examining real-world challenges facing cities and urban environments around the world. The Spring 2025 series is organized by Assistant Professors Takahiro Yabe, Qi Sun, and Graham Dove.
