Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory

Vision-language pre-training (VLP) models exhibit remarkable capabilities in comprehending both images and text, yet they remain susceptible to multimodal adversarial examples (AEs). Strengthening attacks and uncovering vulnerabilities, especially common issues in VLP models (e.g., high transferable...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Gao, Sensen, Jia, Xiaojun, Ren, Xuhong, Tsang, Ivor, Guo, Qing
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!