Towards robust sensing for Autonomous Vehicles: An adversarial perspective
arXiv:2007.10115 · doi:10.1109/MSP.2020.2985363
Abstract
Autonomous Vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions. Fundamental building blocks of such systems are sensors and classifiers that process ultrasound, RADAR, GPS, LiDAR and camera signals~\cite{Khan2018}. It is of primary importance that the resulting decisions are robust to perturbations, which can take the form of different types of nuisances and data transformations, and can even be adversarial perturbations (APs). Adversarial perturbations are purposefully crafted alterations of the environment or of the sensory measurements, with the objective of attacking and defeating the autonomous systems. A careful evaluation of the vulnerabilities of their sensing system(s) is necessary in order to build and deploy safer systems in the fast-evolving domain of AVs. To this end, we survey the emerging field of sensing in adversarial settings: after reviewing adversarial attacks on sensing modalities for autonomous systems, we discuss countermeasures and present future research directions.
References in corpus (11)
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Synthesizing Robust Adversarial Examples
- Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
- Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
- Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
- DARTS: Deceiving Autonomous Cars with Toxic Signs
- Robustness of classifiers: from adversarial to random noise
- On Physical Adversarial Patches for Object Detection
- Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
- Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models
- Hold me tight! Influence of discriminative features on deep network boundaries