Feedback-based Modal Mutual Search for Attacking Vision-Language Pre-training Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ding, Renhua, Zhang, Xinze, Yang, Xiao, He, Kun
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
by: Kim, Sanghwan, et al.
Published: (2024)

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
by: Yang, Qi, et al.
Published: (2025)

Post-pre-training for Modality Alignment in Vision-Language Foundation Models
by: Yamaguchi, Shin'ya, et al.
Published: (2025)

Practical Continual Forgetting for Pre-trained Vision Models
by: Zhao, Hongbo, et al.
Published: (2025)

Multi-Modal Adapter for Vision-Language Models
by: Seputis, Dominykas, et al.
Published: (2024)

Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
by: Verma, Sahil, et al.
Published: (2023)

Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines
by: Zhang, Zhixin, et al.
Published: (2024)

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
by: Zheng, Weijie, et al.
Published: (2024)

A Two-Stage Globally-Diverse Adversarial Attack for Vision-Language Pre-training Models
by: Chen, Wutao, et al.
Published: (2026)

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

Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models
by: Hu, Yuanwei, et al.
Published: (2026)

ChatGPT Encounters Morphing Attack Detection: Zero-Shot MAD with Multi-Modal Large Language Models and General Vision Models
by: Zhang, Haoyu, et al.
Published: (2025)

Pre-trained Vision-Language Models Learn Discoverable Visual Concepts
by: Zang, Yuan, et al.
Published: (2024)

Multi-modal Vision Pre-training for Medical Image Analysis
by: Rui, Shaohao, et al.
Published: (2024)

3D Modality-Aware Pre-training for Vision-Language Model in MRI Multi-organ Abnormality Detection
by: Zhu, Haowen, et al.
Published: (2026)

Pre-training Vision Transformers with Formula-driven Supervised Learning
by: Kataoka, Hirokatsu, et al.
Published: (2022)

Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
by: Peng, Bincheng, et al.
Published: (2026)

ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement
by: Rao, Zhefan, et al.
Published: (2024)

Babel: A Scalable Pre-trained Model for Multi-Modal Sensing via Expandable Modality Alignment
by: Dai, Shenghong, et al.
Published: (2024)

Jailbreaking Vision-Language Models Through the Visual Modality
by: Azulay, Aharon, et al.
Published: (2026)

Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-training
by: Qin, Jiuming, et al.
Published: (2024)

RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models
by: Lin, Xiang, et al.
Published: (2025)

Do Pre-trained Vision-Language Models Encode Object States?
by: Newman, Kaleb, et al.
Published: (2024)

Gradient-based Fine-Tuning through Pre-trained Model Regularization
by: Liu, Xuanbo, et al.
Published: (2025)

Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints
by: Freiberger, Matthias, et al.
Published: (2023)

Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack
by: Liu, Xin, et al.
Published: (2025)

Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training
by: Zhang, Xinsong, et al.
Published: (2025)

CapRecover: A Cross-Modality Feature Inversion Attack Framework on Vision Language Models
by: Xiu, Kedong, et al.
Published: (2025)

Dataset Ownership Verification in Contrastive Pre-trained Models
by: Xie, Yuechen, et al.
Published: (2025)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
by: Cui, Kaiyuan, et al.
Published: (2026)

Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey
by: Wang, Xiao, et al.
Published: (2023)

SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models
by: Tahboub, Hamza, et al.
Published: (2025)

MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations
by: Zhang, Ziyang, et al.
Published: (2025)

Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training
by: Bawazir, Ameera, et al.
Published: (2024)

TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
by: Hu, Yuanze, et al.
Published: (2025)

Robust Pre-Training of Medical Vision-and-Language Models with Domain-Invariant Multi-Modal Masked Reconstruction
by: Filvantorkaman, Melika, et al.
Published: (2026)

MoRE: Multi-Modal Contrastive Pre-training with Transformers on X-Rays, ECGs, and Diagnostic Report
by: Thapa, Samrajya, et al.
Published: (2024)

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
by: Xu, Yuanzhi, et al.
Published: (2026)

MAFA: Managing False Negatives for Vision-Language Pre-training
by: Byun, Jaeseok, et al.
Published: (2023)

Enhancing Vision-Language Model Pre-training with Image-text Pair Pruning Based on Word Frequency
by: Liang, Mingliang, et al.
Published: (2024)