QR-Code

MDAPT: Multi-Modal Depth Adversarial Prompt Tuning to Enhance the Adversarial Robustness of Visual Language Models

Large visual language models like Contrastive Language-Image Pre-training (CLIP), despite their excellent performance, are highly vulnerable to the influence of adversarial examples. This work investigates the accuracy and robustness of visual language models (VLMs) from a novel multi-modal perspect...

Ausführliche Beschreibung

Gespeichert in:
Hauptverfasser: Chao Li, Yonghao Liao, Caichang Ding, Zhiwei Ye
Format: Artigo
Sprache:Inglês
Veröffentlicht: MDPI AG 2025-01-01
Schriftenreihe:Sensors
Schlagworte:
multi-modal
adversarial robustness
visual language models
prompt tuning
Online-Zugang:https://www.mdpi.com/1424-8220/25/1/258
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!

Ähnliche Einträge