In a joint team between BMW and TUM, we investigate the robustness of Convolutional Neural Network (CNN) deployment on embedded systems, particularly the robustness against adversarial attacks in automotive application scenarios.
In the paper titled "BreakingBED - Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks", the authors present evaluation methods to simplify the comparison between CNNs under various attack schemes.The authors are Manoj Rohit Vemparala, Alexander Frickenstein, Nael Fasfous, Lukas Frickenstein, Qi Zhao, Sabine Franziska Kuhn, Daniel Ehrhardt, Yuankai Wu, Christian Unger, Naveen Shankar Nagaraja, and Walter Stechele.
This paper has been accepted for presentation at the Intelligent Systems Conference (IntelliSys). IntelliSys 2021 will focus in areas of intelligent systems and artificial intelligence and how it applies to the real world. IntelliSys provides a leading international forum that brings together researchers and practitioners from diverse fields with the purpose of exploring the fundamental roles, interactions as well as practical impacts of Artificial Intelligence.
Intelligent Systems Conference (IntelliSys), September 2-3, 2021. https://saiconference.com/IntelliSys