The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challenge for the deployment of ML-based systems in safety- and security-critical environments like autonomous driving, disease...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-06
Hauptverfasser:	Assion, Felix, Schlicht, Peter, Florens Greßner, Günther, Wiebke, Hüger, Fabian, Schmidt, Nico, Rasheed, Umair
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer vision Image segmentation Machine learning Object recognition Perturbation Semantic segmentation Semantics Taxonomy Unmanned aerial vehicles Vision systems
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!