Image de couverture de livre

Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xiu, Yanming, Jiang, Zhengyuan, Gong, Neil Zhenqiang, Gorlatova, Maria
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ViDDAR: Vision Language Model-Based Task-Detrimental Content Detection for Augmented Reality
par: Xiu, Yanming, et autres
Publié: (2025)

Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approach
par: Xiu, Yanming, et autres
Publié: (2025)

Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble
par: Duan, Lin, et autres
Publié: (2025)

User Prompting Strategies and Prompt Enhancement Methods for Open-Set Object Detection in XR Environments
par: Lin, Junfeng, et autres
Publié: (2026)

Robustness of Vision Foundation Models to Common Perturbations
par: Liu, Hongbin, et autres
Publié: (2026)

Toward Safe, Trustworthy and Realistic Augmented Reality User Experience
par: Xiu, Yanming
Publié: (2025)

A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality
par: Chen, Rongqian, et autres
Publié: (2025)

SafeText: Safe Text-to-image Models via Aligning the Text Encoder
par: Hu, Yuepeng, et autres
Publié: (2025)

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
par: Jiang, Zhengyuan, et autres
Publié: (2025)

Watermark-based Attribution of AI-Generated Content
par: Jiang, Zhengyuan, et autres
Publié: (2024)

Demonstrating Visual Information Manipulation Attacks in Augmented Reality: A Hands-On Miniature City-Based Setup
par: Xiu, Yanming, et autres
Publié: (2025)

EditTrack: Detecting and Attributing AI-assisted Image Editing
par: Jiang, Zhengyuan, et autres
Publié: (2025)

Certifiably Robust Image Watermark
par: Jiang, Zhengyuan, et autres
Publié: (2024)

Stable Signature is Unstable: Removing Image Watermark from Diffusion Models
par: Hu, Yuepeng, et autres
Publié: (2024)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
par: Li, Juncheng, et autres
Publié: (2025)

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
par: Jia, Yuqi, et autres
Publié: (2024)

VideoMarkBench: Benchmarking Robustness of Video Watermarking
par: Jiang, Zhengyuan, et autres
Publié: (2025)

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
par: Zhang, Jinghuai, et autres
Publié: (2022)

Visual Hallucinations of Multi-modal Large Language Models
par: Huang, Wen, et autres
Publié: (2024)

CapRecover: A Cross-Modality Feature Inversion Attack Framework on Vision Language Models
par: Xiu, Kedong, et autres
Publié: (2025)

Say It, See It: A Systematic Evaluation on Speech-Based 3D Content Generation Methods in Augmented Reality
par: Xiu, Yanming, et autres
Publié: (2025)

One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models
par: Zhao, Jiale, et autres
Publié: (2025)

Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation
par: Yu, Hong-Tao, et autres
Publié: (2025)

Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models
par: Liu, Hongbin, et autres
Publié: (2024)

HarassGuard: Detecting Harassment Behaviors in Social Virtual Reality with Vision-Language Models
par: Lee, Junhee, et autres
Publié: (2026)

Refusing Safe Prompts for Multi-modal Large Language Models
par: Shao, Zedian, et autres
Publié: (2024)

Beyond Augmentation: Empowering Model Robustness under Extreme Capture Environments
par: Gong, Yunpeng, et autres
Publié: (2024)

Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models
par: Liu, Zhongye, et autres
Publié: (2024)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
par: Li, Jiayu, et autres
Publié: (2025)

BLEnD-Vis: Benchmarking Multimodal Cultural Understanding in Vision Language Models
par: Tan, Bryan Chen Zhengyu, et autres
Publié: (2025)

ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models
par: Li, Zhaoyang, et autres
Publié: (2025)

WebInject: Prompt Injection Attack to Web Agents
par: Wang, Xilong, et autres
Publié: (2025)

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
par: Shao, Zedian, et autres
Publié: (2026)

Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
par: Waseda, Futa, et autres
Publié: (2025)

GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content Creation
par: Dai, Peng, et autres
Publié: (2024)

MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models
par: Hua, Hang, et autres
Publié: (2024)

Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction
par: Li, Yuanbo, et autres
Publié: (2026)

Web Artifact Attacks Disrupt Vision Language Models
par: Qraitem, Maan, et autres
Publié: (2025)

Practical Region-level Attack against Segment Anything Models
par: Shen, Yifan, et autres
Publié: (2024)

Deep Learning for Virtual Reality User Identification: A Benchmark
par: Frizzo, Davide, et autres
Publié: (2026)