Imagen de Portada

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Balakrishnan, Ravikumar, Mendapara, Sanket, Garg, Ankit
Formato:	Preprint
Publicado:	2026
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

One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations
por: Balakrishnan, Ravikumar, et al.
Publicado: (2026)

Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
por: Waseda, Futa, et al.
Publicado: (2025)

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models
por: Ying, Zonghao, et al.
Publicado: (2026)

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models
por: Balakrishnan, Ravikumar, et al.
Publicado: (2025)

VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models
por: Phute, Mansi, et al.
Publicado: (2025)

Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model
por: Cheng, Hao, et al.
Publicado: (2024)

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

Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models
por: Cheng, Hao, et al.
Publicado: (2024)

Typographic Text Generation with Off-the-Shelf Diffusion Model
por: Peong, KhayTze, et al.
Publicado: (2024)

DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
por: Jose, Cijo, et al.
Publicado: (2024)

Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models
por: Li, Yueyan, et al.
Publicado: (2025)

Automatic Text Box Placement for Supporting Typographic Design
por: Muraoka, Jun, et al.
Publicado: (2025)

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks
por: Qraitem, Maan, et al.
Publicado: (2024)

Hierarchical Vision-Language Alignment for Text-to-Image Generation via Diffusion Models
por: Johnson, Emily, et al.
Publicado: (2025)

In the Era of Prompt Learning with Vision-Language Models
por: Jha, Ankit
Publicado: (2024)

Fit Pixels, Get Labels: Meta-learned Implicit Networks for Image Segmentation
por: Vyas, Kushal, et al.
Publicado: (2025)

Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Models
por: He, Zoe Wanying, et al.
Publicado: (2025)

Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
por: Hufe, Lorenz, et al.
Publicado: (2025)

SineProject: Machine Unlearning for Stable Vision Language Alignment
por: Garg, Arpit, et al.
Publicado: (2025)

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
por: Chen, Tianle, et al.
Publicado: (2026)

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models
por: Wang, Haobo, et al.
Publicado: (2026)

Mirage: Unveiling Hidden Artifacts in Synthetic Images with Large Vision-Language Models
por: Sharma, Pranav, et al.
Publicado: (2025)

SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
por: Cao, Yue, et al.
Publicado: (2024)

OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model
por: Singh, Ishika, et al.
Publicado: (2025)

Revisiting Vision Language Foundations for No-Reference Image Quality Assessment
por: Yadav, Ankit, et al.
Publicado: (2025)

PiTe: Pixel-Temporal Alignment for Large Video-Language Model
por: Liu, Yang, et al.
Publicado: (2024)

Language-Image Alignment with Fixed Text Encoders
por: Yang, Jingfeng, et al.
Publicado: (2025)

PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
por: Liang, Wenqi, et al.
Publicado: (2025)

PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks
por: Xu, Jingning, et al.
Publicado: (2026)

Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment
por: Liu, Yang, et al.
Publicado: (2025)

Image Recognition with Vision and Language Embeddings of VLMs
por: Volkov, Illia, et al.
Publicado: (2025)

Pixel Is Not a Barrier: An Effective Evasion Attack for Pixel-Domain Diffusion Models
por: Shih, Chun-Yen, et al.
Publicado: (2024)

FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation
por: Li, Bingyu, et al.
Publicado: (2025)

Detecting Text Manipulation in Images using Vision Language Models
por: Vidit, Vidit, et al.
Publicado: (2025)

Embedding Textual Information in Images Using Quinary Pixel Combinations
por: Kandala, A V Uday Kiran
Publicado: (2026)

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
por: Liu, Zhiheng, et al.
Publicado: (2026)

GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing
por: Ma, Xianzhi, et al.
Publicado: (2025)

SPOOF: Simple Pixel Operations for Out-of-Distribution Fooling
por: Gupta, Ankit, et al.
Publicado: (2025)

Reading Between the Lanes: Text VideoQA on the Road
por: Tom, George, et al.
Publicado: (2023)

Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation
por: Bao, Muyi, et al.
Publicado: (2026)