Buchumschlag

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Haobo, Luo, Weiqi, Jia, Xiaojun, Cao, Xiaochun
Format:	Preprint
Veröffentlicht:	2026
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 Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment
von: Wang, Haobo, et al.
Veröffentlicht: (2026)

Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
von: Jia, Xiaojun, et al.
Veröffentlicht: (2024)

ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers
von: Cao, Hanwen, et al.
Veröffentlicht: (2025)

Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory
von: Gao, Sensen, et al.
Veröffentlicht: (2024)

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
von: Liang, Jiawei, et al.
Veröffentlicht: (2024)

PersGuard: Preventing Malicious Personalization via Backdoor Attacks on Pre-trained Text-to-Image Diffusion Models
von: Liu, Xinwei, et al.
Veröffentlicht: (2025)

LatRef-Diff: Latent and Reference-Guided Diffusion for Facial Attribute Editing and Style Manipulation
von: Huang, Wenmin, et al.
Veröffentlicht: (2026)

Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks
von: Xie, Peng, et al.
Veröffentlicht: (2024)

When and Where to Attack? Stage-wise Attention-Guided Adversarial Attack on Large Vision Language Models
von: Kwak, Jaehyun, et al.
Veröffentlicht: (2026)

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
von: Liang, Siyuan, et al.
Veröffentlicht: (2024)

Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models
von: Guo, Qi, et al.
Veröffentlicht: (2024)

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
von: Cao, Yiming, et al.
Veröffentlicht: (2025)

Text Adversarial Attacks with Dynamic Outputs
von: Wang, Wenqiang, et al.
Veröffentlicht: (2025)

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks
von: Fang, Hao, et al.
Veröffentlicht: (2024)

InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models
von: Wang, Xunguang, et al.
Veröffentlicht: (2023)

Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection
von: Zhu, Jiayi, et al.
Veröffentlicht: (2025)

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
von: Liu, Xinwei, et al.
Veröffentlicht: (2025)

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
von: Liang, Jiawei, et al.
Veröffentlicht: (2024)

Hierarchical Refinement of Universal Multimodal Attacks on Vision-Language Models
von: Zhang, Peng-Fei, et al.
Veröffentlicht: (2026)

MTAttack: Multi-Target Backdoor Attacks against Large Vision-Language Models
von: Wang, Zihan, et al.
Veröffentlicht: (2025)

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack
von: Gu, Chenhe, et al.
Veröffentlicht: (2025)

Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction
von: Li, Yuanbo, et al.
Veröffentlicht: (2026)

PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
von: Guo, Qi, et al.
Veröffentlicht: (2025)

Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks
von: Zhao, Yingying, et al.
Veröffentlicht: (2026)

Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models
von: Wang, Ruofan, et al.
Veröffentlicht: (2025)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
von: Liang, Siyuan, et al.
Veröffentlicht: (2023)

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack
von: Ghosh, Akash, et al.
Veröffentlicht: (2026)

AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing
von: Huang, Wenmin, et al.
Veröffentlicht: (2026)

Improving Transferable Targeted Attacks with Feature Tuning Mixup
von: Liang, Kaisheng, et al.
Veröffentlicht: (2024)

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
von: Zhang, Tianyuan, et al.
Veröffentlicht: (2024)

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

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
von: Zhong, Zhiyuan, et al.
Veröffentlicht: (2025)

PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
von: Mei, Hefei, et al.
Veröffentlicht: (2026)

When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models
von: Yan, Yuping, et al.
Veröffentlicht: (2025)

Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models
von: Jia, Xiaojun, et al.
Veröffentlicht: (2025)

TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularization
von: Guesmi, Amira, et al.
Veröffentlicht: (2025)

Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment
von: Li, Jiaqing, et al.
Veröffentlicht: (2026)

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking
von: Fu, Jiyuan, et al.
Veröffentlicht: (2026)

Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing
von: Weng, Juanjuan, et al.
Veröffentlicht: (2024)

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