X-Detect: explainable adversarial patch detection for object detectors in retail

Object detection models, which are widely used in various domains (such as retail), have been shown to be vulnerable to adversarial attacks. Existing methods for detecting adversarial attacks on object detectors have had difficulty detecting new real-life attacks. We present X-Detect, a novel advers...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Machine learning 2024-09, Vol.113 (9), p.6273-6292
Hauptverfasser:	Hofman, Omer, Giloni, Amit, Hayun, Yarin, Morikawa, Ikuya, Shimizu, Toshiya, Elovici, Yuval, Shabtai, Asaf
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Computer Science Control Datasets Detectors False alarms Feature extraction Machine Learning Mechatronics Natural Language Processing (NLP) Object recognition Robotics Sensors Simulation and Modeling Superstores
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!