COE Dept. Seminar - "Adversarial Patch Attacks against Vision-based Vehicle Recognition Systems" - Dr. Abdul Jabbar Siddiqui
=====================================================================================
College of Computing and Mathematics
Computer Engineering Department
=====================================================================================
Presents Public Seminar
"Adversarial Patch Attacks against Vision-based Vehicle Recognition Systems"
Date: Wednesday, February 15, 2023,
Time: 02:30 PM – 03:30 PM
Location: Bldg. 22, Room 132
Speaker:
Dr. Abdul Jabbar Siddiqui
Assistant Professor
Computer Engineering Department, KFUPM.
Abstract:
In smart cities, connected and automated surveillance systems play an essential role in ensuring the safety and security of life, property, critical infrastructures, and cyber-physical systems. The recent trend of such surveillance systems has been to embrace the use of advanced deep learning models such as convolutional neural networks for the task of detection, monitoring, or tracking. In this paper, we focus on the security of an automated surveillance system that is responsible for the vehicle make and model recognition (VMMR). We introduce an adversarial attack against such VMMR systems through adversarially learned patches. We demonstrate the effectiveness of the developed adversarial patches against VMMR through experimental evaluations on a real-world vehicle surveillance dataset.
In addition, we propose a lightweight defense method called SIHFR (stands for Symmetric Image-Half Flip and Replace) to eliminate the effect of adversarial patches on VMMR performance. Through experimental evaluations, we investigate the robustness of the proposed defense method under varying patch placement strategies and patch sizes. The proposed defense method adds a minimal overhead of less than 2ms per image (on average) and succeeds in enhancing VMMR performance. This work shall guide future studies to develop smart city VMMR surveillance systems that are robust to cyber-physical attacks based on adversarially learned patches.
Speaker Bio:
Dr. Abdul Jabbar is an Assistant Professor at the Computer Engineering Department and an affiliate of the IRC for Intelligent Secure Systems at the King Fahd University of Petroleum and Minerals (KFUPM). Before joining KFUPM, he worked as a researcher with the Intelligent Transportation Systems Group at the National Research Council of Canada. He earned a PhD and an M.Sc. in Electrical and Computer Engineering from the University of Ottawa (in 2021 and 2015, respectively). His research interests include computer vision, intelligent transportation systems, the internet of things, cyber-physical systems security, and adversarial machine learning. He is actively exploring innovative applications of visual intelligence and machine learning in solving contemporary problems related to the energy, oil and gas, construction, and transportation sectors.
All faculty, researchers and graduate students are invited to attend.
=====================================================================================
Computer Engineering Department, College of Computing and Mathematics
Telephone: +966 (13) 860 2110, Email: c-coe@kfupm.edu.sa, Website: www.kfupm.edu.sa/departments/coe/
Copyright © 2014 King Fahd University of Petroleum & Minerals
=====================================================================================