Image de couverture de livre

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gu, Chenhe, Gu, Jindong, Hua, Andong, Qin, Yao
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving Adversarial Transferability via Model Alignment
par: Ma, Avery, et autres
Publié: (2023)

Initialization Matters for Adversarial Transfer Learning
par: Hua, Andong, et autres
Publié: (2023)

Transferable Adversarial Attacks on Black-Box Vision-Language Models
par: Hu, Kai, et autres
Publié: (2025)

Improving Transferability of Adversarial Examples via Bayesian Attacks
par: Li, Qizhang, et autres
Publié: (2023)

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
par: Luo, Haochen, et autres
Publié: (2024)

$Δ\mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
par: Zhu, Lin, et autres
Publié: (2025)

Benchmarking Transferable Adversarial Attacks
par: Jin, Zhibo, et autres
Publié: (2024)

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
par: Huang, Linhao, et autres
Publié: (2025)

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
par: Hua, Andong, et autres
Publié: (2025)

Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
par: Xu, Haochuan, et autres
Publié: (2025)

Improved Alignment of Modalities in Large Vision Language Models
par: Jangra, Kartik, et autres
Publié: (2025)

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
par: Fang, Zhengwei, et autres
Publié: (2022)

MMRL: Multi-Modal Representation Learning for Vision-Language Models
par: Guo, Yuncheng, et autres
Publié: (2025)

Similarity of Neural Architectures using Adversarial Attack Transferability
par: Hwang, Jaehui, et autres
Publié: (2022)

Boosting Adversarial Transferability via Ensemble Non-Attention
par: Zou, Yipeng, et autres
Publié: (2025)

Boosting Adversarial Transferability via Residual Perturbation Attack
par: Peng, Jinjia, et autres
Publié: (2025)

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
par: Jia, Xiaojun, et autres
Publié: (2025)

Improving the Transferability of Adversarial Attacks by an Input Transpose
par: Wan, Qing, et autres
Publié: (2025)

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
par: Li, Teng, et autres
Publié: (2025)

Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro
par: Tang, Kenan, et autres
Publié: (2026)

Ultrasound Vision-Language Alignment via Contrastive Learning
par: Lyu, Zhuoyang, et autres
Publié: (2026)

Bag of Tricks to Boost Adversarial Transferability
par: Zhang, Zeliang, et autres
Publié: (2024)

Enabling Heterogeneous Adversarial Transferability via Feature Permutation Attacks
par: Wu, Tao, et autres
Publié: (2025)

RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment
par: Gu, Difei, et autres
Publié: (2025)

Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
par: Liu, Zhenyu, et autres
Publié: (2024)

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization
par: Zhang, Yechao, et autres
Publié: (2025)

Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?
par: Chen, Shuo, et autres
Publié: (2023)

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
par: Huang, Hanxun, et autres
Publié: (2025)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
par: Cui, Kaiyuan, et autres
Publié: (2026)

FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
par: Yang, Hunmin, et autres
Publié: (2024)

Fairness-Aware Fine-Tuning of Vision-Language Models for Medical Glaucoma Diagnosis
par: Gu, Zijian, et autres
Publié: (2025)

Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
par: Xiao, Qingxin, et autres
Publié: (2026)

Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models
par: Cheng, Hao, et autres
Publié: (2024)

Dynamic Adversarial Attacks on Autonomous Driving Systems
par: Chahe, Amirhosein, et autres
Publié: (2023)

Personalized Vision via Visual In-Context Learning
par: Jiang, Yuxin, et autres
Publié: (2025)

Transferable Adversarial Attacks on SAM and Its Downstream Models
par: Xia, Song, et autres
Publié: (2024)

Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
par: Dalal, Dwip, et autres
Publié: (2025)

Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams
par: Wang, Ziqiang, et autres
Publié: (2024)

Dynamic Parameter Optimization for Highly Transferable Transformation-Based Attacks
par: Liang, Jiaming, et autres
Publié: (2025)

Transform-Dependent Adversarial Attacks
par: Tan, Yaoteng, et autres
Publié: (2024)