Abstract Autonomous vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions. Fundamental blocks for inferences are sensory systems and classifiers that process ultrasound, RADAR, GPS, LiDAR and camera signals. In particular, decisions should be robust to perturbations, which may include purposefully crafted alterations of the environment or of the sensory measurements. These alterations are known as adversarial perturbations.
To build and deploy safer systems in the fast-evolving field of autonomous vehicles, a continuous evaluation of the vulnerabilities of their sensing system(s) is necessary. To this end, in this paper we survey the emerging field of sensing in adversarial settings: after reviewing adversarial attacks on sensing modalities for autonomous systems, we discuss existing countermeasures and present future research directions.
Links Paper coming soon