Imagen de Portada

When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dai, Aobotao, Ma, Xinyu, Chen, Lei, Li, Songze, Wang, Lin
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment
por: Zhang, Weiming, et al.
Publicado: (2025)

When Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning
por: Huang, Tairan, et al.
Publicado: (2026)

Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs
por: Li, Haoyuan, et al.
Publicado: (2025)

XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs
por: Hu, Chengyin, et al.
Publicado: (2026)

Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers
por: Wang, Jiancheng, et al.
Publicado: (2026)

Toward Inherently Robust VLMs Against Visual Perception Attacks
por: MohajerAnsari, Pedram, et al.
Publicado: (2025)

An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs
por: Luo, Zhi, et al.
Publicado: (2025)

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
por: Zhang, Lei, et al.
Publicado: (2025)

SkiP: When to Skip and When to Refine for Efficient Robot Manipulation
por: Dai, Mingtong, et al.
Publicado: (2026)

Rethinking Knowledge in Distillation: An In-context Sample Retrieval Perspective
por: Zhu, Jinjing, et al.
Publicado: (2025)

MIGA: Mutual Information-Guided Attack on Denoising Models for Semantic Manipulation
por: Li, Guanghao, et al.
Publicado: (2025)

When Semantic Segmentation Meets Frequency Aliasing
por: Chen, Linwei, et al.
Publicado: (2024)

FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection
por: Li, Yongze, et al.
Publicado: (2025)

Multimodal Models Meet Presentation Attack Detection on ID Documents
por: Villanueva, Marina, et al.
Publicado: (2026)

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

Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
por: Qiao, Yuxuan, et al.
Publicado: (2024)

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

DRAG: Data Reconstruction Attack using Guided Diffusion
por: Lei, Wa-Kin, et al.
Publicado: (2025)

A Survey and Evaluation of Adversarial Attacks for Object Detection
por: Nguyen, Khoi Nguyen Tiet, et al.
Publicado: (2024)

When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance
por: Cao, Jinjin, et al.
Publicado: (2025)

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

Physical Adversarial Attack meets Computer Vision: A Decade Survey
por: Wei, Hui, et al.
Publicado: (2022)

Mixture-of-Attack-Experts with Class Regularization for Unified Physical-Digital Face Attack Detection
por: Chen, Shunxin, et al.
Publicado: (2025)

Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving
por: Zeng, Xinyu, et al.
Publicado: (2026)

Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation
por: Chu, Tianyi, et al.
Publicado: (2024)

T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
por: Yeh, Chen, et al.
Publicado: (2024)

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
por: Fang, Hao, et al.
Publicado: (2024)

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
por: Chen, Jianlang, et al.
Publicado: (2024)

MBMamba: When Memory Buffer Meets Mamba for Structure-Aware Image Deblurring
por: Gao, Hu, et al.
Publicado: (2025)

Invisible Backdoor Attack against Self-supervised Learning
por: Zhang, Hanrong, et al.
Publicado: (2024)

Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
por: Wang, Hao, et al.
Publicado: (2026)

When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models
por: Hu, Chengyin, et al.
Publicado: (2026)

Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale
por: Li, Songze, et al.
Publicado: (2025)

SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation
por: Han, Dongshen, et al.
Publicado: (2023)

NoPain: No-box Point Cloud Attack via Optimal Transport Singular Boundary
por: Li, Zezeng, et al.
Publicado: (2025)

When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification
por: Pang, Zirui, et al.
Publicado: (2025)

AdvGPS: Adversarial GPS for Multi-Agent Perception Attack
por: Li, Jinlong, et al.
Publicado: (2024)

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

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
por: Li, Juncheng, et al.
Publicado: (2025)

Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition
por: Zhang, Wei, et al.
Publicado: (2026)