Imagen de Portada

Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hu, Chengyin, Dong, Yuxian, Guo, Yikun, Chen, Xiang, Wu, Junqi, Long, Jiahuan, Wei, Yiwei, Jiang, Tingsong, Yao, Wen
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

Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems
por: Hu, Chengyin, et al.
Publicado: (2026)

CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors
por: Long, Jiahuan, et al.
Publicado: (2025)

Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability
por: Chen, Xiang, et al.
Publicado: (2026)

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

CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models
por: Chen, Xiang, et al.
Publicado: (2026)

Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations
por: Liu, Hanqing, et al.
Publicado: (2025)

Robust SAM: On the Adversarial Robustness of Vision Foundation Models
por: Long, Jiahuan, et al.
Publicado: (2025)

PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking
por: Long, Jiahuan, et al.
Publicado: (2025)

FR-Mamba: Time-Series Physical Field Reconstruction Based on State Space Model
por: Long, Jiahuan, et al.
Publicado: (2025)

A Semantic Decoupling-Based Two-Stage Rainy-Day Attack for Revealing Weather Robustness Deficiencies in Vision-Language Models
por: Hu, Chengyin, et al.
Publicado: (2026)

Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid
por: Tiliwalidi, Kalibinuer, et al.
Publicado: (2024)

Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
por: Long, Jiahuan, et al.
Publicado: (2025)

Improving the Transferability of Adversarial Examples by Feature Augmentation
por: Wang, Donghua, et al.
Publicado: (2024)

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

Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models
por: Long, Jiahuan, et al.
Publicado: (2025)

Adversarial Examples in the Physical World: A Survey
por: Wang, Jiakai, et al.
Publicado: (2023)

From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG
por: Han, Jiaju, et al.
Publicado: (2026)

JailWAM: Jailbreaking World Action Models in Robot Control
por: Liu, Hanqing, et al.
Publicado: (2026)

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

Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models
por: Yan, Shihui, et al.
Publicado: (2026)

Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization
por: Wang, Donghua, et al.
Publicado: (2024)

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection
por: Strack, Lukas, et al.
Publicado: (2023)

The Outline of Deception: Physical Adversarial Attacks on Traffic Signs Using Edge Patches
por: Ji, Haojie, et al.
Publicado: (2025)

APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching
por: Nong, Yu, et al.
Publicado: (2024)

SwitchPatch: Physical Adversarial Attack Strategy with Switchable Adversarial Objectives
por: Jiang, Hanrui, et al.
Publicado: (2025)

BadPatch: Diffusion-Based Generation of Physical Adversarial Patches
por: Wang, Zhixiang, et al.
Publicado: (2024)

Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving
por: Zhu, Zihui, et al.
Publicado: (2026)

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation
por: Aggarwal, Aarush, et al.
Publicado: (2026)

PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
por: Wei, Zichao, et al.
Publicado: (2025)

LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment
por: Long, Jiahuan, et al.
Publicado: (2025)

Revisiting Vulnerability Patch Identification on Data in the Wild
por: Irsan, Ivana Clairine, et al.
Publicado: (2026)

Interpretability-Aware Vision Transformer
por: Qiang, Yao, et al.
Publicado: (2023)

AutoPatch: Multi-Agent Framework for Patching Real-World CVE Vulnerabilities
por: Seo, Minjae, et al.
Publicado: (2025)

Vision Graph Prompting via Semantic Low-Rank Decomposition
por: Ai, Zixiang, et al.
Publicado: (2025)

Fairness-aware Vision Transformer via Debiased Self-Attention
por: Qiang, Yao, et al.
Publicado: (2023)

A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models
por: Zheng, Haonan, et al.
Publicado: (2024)

HeteroMorpheus: Universal Control Based on Morphological Heterogeneity Modeling
por: Hao, YiFan, et al.
Publicado: (2024)

Financial sentiment analysis using FinBERT with application in predicting stock movement
por: Jiang, Tingsong, et al.
Publicado: (2023)

Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilities
por: Zhang, Zikai, et al.
Publicado: (2024)

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
por: Gao, Junqi, et al.
Publicado: (2024)