Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gu, Chenhe, Gu, Jindong, Hua, Andong, Qin, Yao
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improving Adversarial Transferability via Model Alignment
por: Ma, Avery, et al.
Publicado: (2023)

Initialization Matters for Adversarial Transfer Learning
por: Hua, Andong, et al.
Publicado: (2023)

Transferable Adversarial Attacks on Black-Box Vision-Language Models
por: Hu, Kai, et al.
Publicado: (2025)

Improving Transferability of Adversarial Examples via Bayesian Attacks
por: Li, Qizhang, et al.
Publicado: (2023)

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
por: Luo, Haochen, et al.
Publicado: (2024)

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

Benchmarking Transferable Adversarial Attacks
por: Jin, Zhibo, et al.
Publicado: (2024)

Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video Approach
por: Huang, Linhao, et al.
Publicado: (2025)

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
por: Hua, Andong, et al.
Publicado: (2025)

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

Improved Alignment of Modalities in Large Vision Language Models
por: Jangra, Kartik, et al.
Publicado: (2025)

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
por: Fang, Zhengwei, et al.
Publicado: (2022)

MMRL: Multi-Modal Representation Learning for Vision-Language Models
por: Guo, Yuncheng, et al.
Publicado: (2025)

Similarity of Neural Architectures using Adversarial Attack Transferability
por: Hwang, Jaehui, et al.
Publicado: (2022)

Boosting Adversarial Transferability via Ensemble Non-Attention
por: Zou, Yipeng, et al.
Publicado: (2025)

Boosting Adversarial Transferability via Residual Perturbation Attack
por: Peng, Jinjia, et al.
Publicado: (2025)

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
por: Jia, Xiaojun, et al.
Publicado: (2025)

Improving the Transferability of Adversarial Attacks by an Input Transpose
por: Wan, Qing, et al.
Publicado: (2025)

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
por: Li, Teng, et al.
Publicado: (2025)

Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro
por: Tang, Kenan, et al.
Publicado: (2026)

Ultrasound Vision-Language Alignment via Contrastive Learning
por: Lyu, Zhuoyang, et al.
Publicado: (2026)

Bag of Tricks to Boost Adversarial Transferability
por: Zhang, Zeliang, et al.
Publicado: (2024)

Enabling Heterogeneous Adversarial Transferability via Feature Permutation Attacks
por: Wu, Tao, et al.
Publicado: (2025)

RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment
por: Gu, Difei, et al.
Publicado: (2025)

Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
por: Liu, Zhenyu, et al.
Publicado: (2024)

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization
por: Zhang, Yechao, et al.
Publicado: (2025)

Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?
por: Chen, Shuo, et al.
Publicado: (2023)

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
por: Huang, Hanxun, et al.
Publicado: (2025)

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

FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
por: Yang, Hunmin, et al.
Publicado: (2024)

Fairness-Aware Fine-Tuning of Vision-Language Models for Medical Glaucoma Diagnosis
por: Gu, Zijian, et al.
Publicado: (2025)

Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
por: Xiao, Qingxin, et al.
Publicado: (2026)

Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models
por: Cheng, Hao, et al.
Publicado: (2024)

Dynamic Adversarial Attacks on Autonomous Driving Systems
por: Chahe, Amirhosein, et al.
Publicado: (2023)

Personalized Vision via Visual In-Context Learning
por: Jiang, Yuxin, et al.
Publicado: (2025)

Transferable Adversarial Attacks on SAM and Its Downstream Models
por: Xia, Song, et al.
Publicado: (2024)

Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
por: Dalal, Dwip, et al.
Publicado: (2025)

Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams
por: Wang, Ziqiang, et al.
Publicado: (2024)

Dynamic Parameter Optimization for Highly Transferable Transformation-Based Attacks
por: Liang, Jiaming, et al.
Publicado: (2025)

Transform-Dependent Adversarial Attacks
por: Tan, Yaoteng, et al.
Publicado: (2024)