4 papers
The Spectrum Strikes Back: Infrared POV Attacks on Traffic Sign Classification
Michael Kühr, Mevlüt Yildirim, Maximilian Luedecke +2
Traffic sign classification is a crucial task for autonomous vehicles, and numerous attacks against it have been identified. A majority of physical adversarial attacks involve atta…
Toward Inherently Robust VLMs Against Visual Perception Attacks
Pedram MohajerAnsari, Amir Salarpour, Michael Kühr +6
Autonomous vehicles rely on deep neural networks (DNNs) for traffic sign recognition, lane centering, and vehicle detection, yet these models are vulnerable to attacks that induce…
SoK: Security of the Image Processing Pipeline for Camera-based Sensing in Autonomous Vehicles
Michael Kühr, Mohammad Hamad, Pedram MohajerAnsari +2
Cameras capture images that are essential for many safety-critical tasks. To process these images, a complex pipeline with multiple layers is used. Security attacks on this pipelin…
FuzzSense: Towards A Modular Fuzzing Framework for Autonomous Driving Software
Andrew Roberts, Lorenz Teply, Mert D. Pese +3
Fuzz testing to find semantic control vulnerabilities is an essential activity to evaluate the robustness of autonomous driving (AD) software. Whilst there is a preponderance of di…