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...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Chao Li, Yonghao Liao, Caichang Ding, Zhiwei Ye
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2025-01-01
coleção:	Sensors
Assuntos:	multi-modal adversarial robustness visual language models prompt tuning
Acesso em linha:	https://www.mdpi.com/1424-8220/25/1/258
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!