Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction

Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely studies the transferability of attacks on VLP models, resulting in a substantial performance gap from white-box attacks....

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Fu, Jiyuan, Chen, Zhaoyu, Jiang, Kaixun, Guo, Haijing, Wang, Jiafeng, Gao, Shuyong, Zhang, Wenqiang
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Cryptography and Security Computer Science - Multimedia
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!