Buchumschlag

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Tianyuan, Wang, Lu, Zhang, Xinwei, Zhang, Yitong, Jia, Boyi, Liang, Siyuan, Hu, Shengshan, Fu, Qiang, Liu, Aishan, Liu, Xianglong
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving
von: Zhang, Tianyuan, et al.
Veröffentlicht: (2024)

Towards Robust Physical-world Backdoor Attacks on Lane Detection
von: Zhang, Xinwei, et al.
Veröffentlicht: (2024)

Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving
von: Zhang, Tianyuan, et al.
Veröffentlicht: (2025)

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
von: Ying, Zonghao, et al.
Veröffentlicht: (2024)

Manipulating Multimodal Agents via Cross-Modal Prompt Injection
von: Wang, Le, et al.
Veröffentlicht: (2025)

Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles
von: Liu, Jiangfan, et al.
Veröffentlicht: (2025)

Universal Camouflage Attack on Vision-Language Models for Autonomous Driving
von: Kong, Dehong, et al.
Veröffentlicht: (2025)

LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions
von: Zhang, Tianyuan, et al.
Veröffentlicht: (2024)

Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving
von: Liu, Ming, et al.
Veröffentlicht: (2025)

Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography
von: Chung, Nhat, et al.
Veröffentlicht: (2024)

CogMorph: Cognitive Morphing Attacks for Text-to-Image Models
von: Jing, Zonglei, et al.
Veröffentlicht: (2025)

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
von: Liang, Jiawei, et al.
Veröffentlicht: (2024)

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation
von: Jing, Zonglei, et al.
Veröffentlicht: (2025)

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
von: Liang, Siyuan, et al.
Veröffentlicht: (2024)

PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving
von: Fu, Jiyuan, et al.
Veröffentlicht: (2024)

Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks
von: Ying, Zonghao, et al.
Veröffentlicht: (2024)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
von: Zhang, Xinwei, et al.
Veröffentlicht: (2026)

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
von: Liang, Jiawei, et al.
Veröffentlicht: (2024)

GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing
von: Xiao, Yisong, et al.
Veröffentlicht: (2024)

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

MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving
von: Liu, Aishan, et al.
Veröffentlicht: (2025)

Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness
von: Song, Yufei, et al.
Veröffentlicht: (2026)

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

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
von: Zhang, Hangtao, et al.
Veröffentlicht: (2024)

Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving
von: Wang, Yunshen, et al.
Veröffentlicht: (2025)

Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving
von: Zhao, Zongchuang, et al.
Veröffentlicht: (2025)

PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
von: Guo, Qi, et al.
Veröffentlicht: (2025)

RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation
von: Liu, Enguang, et al.
Veröffentlicht: (2025)

ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation
von: Fu, Haoyu, et al.
Veröffentlicht: (2025)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
von: Liang, Siyuan, et al.
Veröffentlicht: (2023)

DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
von: Zhang, Yitong, et al.
Veröffentlicht: (2025)

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
von: Hu, Jin, et al.
Veröffentlicht: (2025)

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
von: Song, Yufei, et al.
Veröffentlicht: (2024)

Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2
von: Zhou, Ziqi, et al.
Veröffentlicht: (2025)

DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
von: Tian, Xiaoyu, et al.
Veröffentlicht: (2024)

X-Driver: Explainable Autonomous Driving with Vision-Language Models
von: Liu, Wei, et al.
Veröffentlicht: (2025)

MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
von: Fu, Haoyu, et al.
Veröffentlicht: (2025)

Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
von: Xiong, Minhao, et al.
Veröffentlicht: (2025)

ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
von: Wang, Yichen, et al.
Veröffentlicht: (2025)