Buchumschlag

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Zeyu, Xie, Cihang, Bartoldson, Brian, Kailkhura, Bhavya
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
von: Bartoldson, Brian R., et al.
Veröffentlicht: (2024)

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
von: Gao, Yipeng, et al.
Veröffentlicht: (2023)

On the Adversarial Robustness of Camera-based 3D Object Detection
von: Xie, Shaoyuan, et al.
Veröffentlicht: (2023)

Revisiting Adversarial Training at Scale
von: Wang, Zeyu, et al.
Veröffentlicht: (2024)

ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
von: Zheng, Haizhong, et al.
Veröffentlicht: (2024)

Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
von: Wang, Sibo, et al.
Veröffentlicht: (2024)

Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
von: Zhou, Dawei, et al.
Veröffentlicht: (2021)

Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models
von: Zheng, Haonan, et al.
Veröffentlicht: (2024)

Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models
von: Yang, Fan, et al.
Veröffentlicht: (2024)

MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models
von: Zhang, Peng-Fei, et al.
Veröffentlicht: (2025)

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
von: Liu, Yanqing, et al.
Veröffentlicht: (2025)

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models
von: Ruan, Shouwei, et al.
Veröffentlicht: (2024)

Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
von: Fu, Jiyuan, et al.
Veröffentlicht: (2024)

NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training
von: Tao, Yiyi, et al.
Veröffentlicht: (2024)

Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning
von: Park, Dongmin, et al.
Veröffentlicht: (2024)

Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
von: Wu, Shihan, et al.
Veröffentlicht: (2024)

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention
von: Duan, Jinhao, et al.
Veröffentlicht: (2025)

TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
von: Wang, Xin, et al.
Veröffentlicht: (2024)

Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking
von: Xu, Long, et al.
Veröffentlicht: (2025)

Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
von: Lv, Kangtao, et al.
Veröffentlicht: (2024)

Rejuvenating image-GPT as Strong Visual Representation Learners
von: Ren, Sucheng, et al.
Veröffentlicht: (2023)

Adversarial Defense in Vision-Language Models: An Overview
von: Fu, Xiaowei, et al.
Veröffentlicht: (2026)

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
von: Zhang, Jiaming, et al.
Veröffentlicht: (2025)

Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
von: Qian, Zhaofang, et al.
Veröffentlicht: (2025)

VILA: On Pre-training for Visual Language Models
von: Lin, Ji, et al.
Veröffentlicht: (2023)

SDPT: Synchronous Dual Prompt Tuning for Fusion-based Visual-Language Pre-trained Models
von: Zhou, Yang, et al.
Veröffentlicht: (2024)

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models
von: Yin, Ziyi, et al.
Veröffentlicht: (2024)

MedCutMix: A Data-Centric Approach to Improve Radiology Vision-Language Pre-training with Disease Awareness
von: Wang, Sinuo, et al.
Veröffentlicht: (2025)

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
von: Yin, Ziyi, et al.
Veröffentlicht: (2023)

Understanding the Multi-modal Prompts of the Pre-trained Vision-Language Model
von: Ma, Shuailei, et al.
Veröffentlicht: (2023)

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
von: Li, Lin, et al.
Veröffentlicht: (2024)

A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models
von: Liang, Yuhan, et al.
Veröffentlicht: (2024)

A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models
von: Mirza, Mujtaba Hussain, et al.
Veröffentlicht: (2026)

Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models
von: Zhang, Zhifang, et al.
Veröffentlicht: (2025)

Adversarial Prompt Tuning for Vision-Language Models
von: Zhang, Jiaming, et al.
Veröffentlicht: (2023)

Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models
von: Kong, Dehong, et al.
Veröffentlicht: (2024)

B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions
von: Zhang, Hao, et al.
Veröffentlicht: (2024)

PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks
von: Xu, Jingning, et al.
Veröffentlicht: (2026)

MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models
von: Miao, Yongzhu, et al.
Veröffentlicht: (2023)

Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
von: Xu, Haochuan, et al.
Veröffentlicht: (2025)