Buchumschlag

DistractMIA: Black-Box Membership Inference on Vision-Language Models via Semantic Distraction

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Tang, Hongyi, Zhu, Zhihao, Yang, Yi
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computer Vision and Pattern Recognition Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models
von: Miyamoto, Ryoto, et al.
Veröffentlicht: (2025)

Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts
von: Sharma, Aditya, et al.
Veröffentlicht: (2024)

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
von: Xu, Haolei, et al.
Veröffentlicht: (2026)

MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems
von: Yang, Peiru, et al.
Veröffentlicht: (2025)

Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions
von: Ha, Jeongsoo, et al.
Veröffentlicht: (2025)

Distracted Robot: How Visual Clutter Undermine Robotic Manipulation
von: Rasouli, Amir, et al.
Veröffentlicht: (2025)

Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory
von: Li, Quanjiang, et al.
Veröffentlicht: (2026)

Rethinking Top Probability from Multi-view for Distracted Driver Behaviour Localization
von: Nguyen, Quang Vinh, et al.
Veröffentlicht: (2024)

P-YOLOv8: Efficient and Accurate Real-Time Detection of Distracted Driving
von: Elshamy, Mohamed R., et al.
Veröffentlicht: (2024)

Towards Black-Box Membership Inference Attack for Diffusion Models
von: Li, Jingwei, et al.
Veröffentlicht: (2024)

Effective Black-Box Multi-Faceted Attacks Breach Vision Large Language Model Guardrails
von: Yang, Yijun, et al.
Veröffentlicht: (2025)

ImitDiff: Transferring Foundation-Model Priors for Distraction Robust Visuomotor Policy
von: Dong, Yuhang, et al.
Veröffentlicht: (2025)

When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
von: Zhao, Beidi, et al.
Veröffentlicht: (2026)

Cross-Camera Distracted Driver Classification through Feature Disentanglement and Contrastive Learning
von: Celona, Luigi, et al.
Veröffentlicht: (2024)

Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving
von: Wang, Lu, et al.
Veröffentlicht: (2025)

PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction Detection
von: Sun, Haibin, et al.
Veröffentlicht: (2025)

Improving Black-Box Generative Attacks via Generator Semantic Consistency
von: Jeong, Jongoh, et al.
Veröffentlicht: (2025)

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
von: Liu, Ziyu, et al.
Veröffentlicht: (2024)

Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distractions
von: Kim, Kyungmin, et al.
Veröffentlicht: (2024)

Towards Infusing Auxiliary Knowledge for Distracted Driver Detection
von: Balappanawar, Ishwar B, et al.
Veröffentlicht: (2024)

Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models
von: Qi, Tao, et al.
Veröffentlicht: (2026)

AI-based Multimodal Biometrics for Detecting Smartphone Distractions: Application to Online Learning
von: Becerra, Alvaro, et al.
Veröffentlicht: (2025)

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
von: Tang, Zhenwei, et al.
Veröffentlicht: (2025)

Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?
von: Amebley, David, et al.
Veröffentlicht: (2025)

Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos
von: Hasan, Md Zahid, et al.
Veröffentlicht: (2023)

Membership Inference Attacks against Large Vision-Language Models
von: Li, Zhan, et al.
Veröffentlicht: (2024)

Robotic Environmental State Recognition with Pre-Trained Vision-Language Models and Black-Box Optimization
von: Kawaharazuka, Kento, et al.
Veröffentlicht: (2024)

Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
von: Wang, Zhengbo, et al.
Veröffentlicht: (2024)

Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models
von: Woo, Sangmin, et al.
Veröffentlicht: (2025)

BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation
von: Li, Feiran, et al.
Veröffentlicht: (2026)

HoneyImage: Verifiable, Harmless, and Stealthy Dataset Ownership Verification for Image Models
von: Zhu, Zhihao, et al.
Veröffentlicht: (2025)

Distraction is All You Need for Multimodal Large Language Model Jailbreaking
von: Yang, Zuopeng, et al.
Veröffentlicht: (2025)

Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
von: Zhan, Yufei, et al.
Veröffentlicht: (2025)

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference
von: Liu, Ziyan, et al.
Veröffentlicht: (2025)

Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks
von: An, Haonan, et al.
Veröffentlicht: (2024)

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
von: Müller, Andreas, et al.
Veröffentlicht: (2024)

DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models
von: Li, Chenyang, et al.
Veröffentlicht: (2026)

MINT-Demo: Membership Inference Test Demonstrator
von: DeAlcala, Daniel, et al.
Veröffentlicht: (2025)

Membership Inference Test: Auditing Training Data in Object Classification Models
von: Mancera, Gonzalo, et al.
Veröffentlicht: (2026)