Image de couverture de livre

Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chung, Nhat, Gao, Sensen, Vu, Tuan-Anh, Zhang, Jie, Liu, Aishan, Lin, Yun, Dong, Jin Song, Guo, Qing
Format:	Preprint
Publié:	2024
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

Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory
par: Gao, Sensen, et autres
Publié: (2024)

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
par: Zhou, Qi, et autres
Publié: (2024)

Universal Camouflage Attack on Vision-Language Models for Autonomous Driving
par: Kong, Dehong, et autres
Publié: (2025)

Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving
par: Wang, Lu, et autres
Publié: (2025)

PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving
par: Fu, Jiyuan, et autres
Publié: (2024)

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
par: Zhang, Tianyuan, et autres
Publié: (2024)

Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
par: Jia, Xiaojun, et autres
Publié: (2024)

Long time behavior of the Vlasov-Maxwell-Fokker-Planck system with a strong external magnetic field
par: Vu, Anh-Tuan
Publié: (2025)

The calculated results of current field and its effects on the process of sediment transport at Dong Bo river mouth (Cua Be), Nha Trang
par: Vu, Tuan Anh
Publié: (2002)

Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion
par: Vu, Tuan-Anh, et autres
Publié: (2023)

Towards Powerful and Practical Patch Attacks for 2D Object Detection in Autonomous Driving
par: Cao, Yuxin, et autres
Publié: (2025)

Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving
par: Zhang, Tianyuan, et autres
Publié: (2025)

Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
par: Zhao, Shuai, et autres
Publié: (2024)

PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
par: Guo, Qi, et autres
Publié: (2025)

ToXCL: A Unified Framework for Toxic Speech Detection and Explanation
par: Hoang, Nhat M., et autres
Publié: (2024)

Attack On Prompt: Backdoor Attack in Prompt-Based Continual Learning
par: Nguyen, Trang, et autres
Publié: (2024)

NutVLM: A Self-Adaptive Defense Framework against Full-Dimension Attacks for Vision Language Models in Autonomous Driving
par: Peng, Xiaoxu, et autres
Publié: (2026)

Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks
par: Xie, Peng, et autres
Publié: (2024)

Autonomous Block Assembly for Boom Cranes with Passive Joint Dynamics: Integrated Vision MPC Control
par: Ebmer, Gerald, et autres
Publié: (2026)

DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Pass
par: Alumootil, Vivek, et autres
Publié: (2025)

Long time behavior for collisional strongly magnetized plasma in three space dimensions
par: Bostan, Mihaï, et autres
Publié: (2023)

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
par: Zhao, Shuai, et autres
Publié: (2024)

Reading $\neq$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models
par: Zhou, Heng, et autres
Publié: (2026)

Towards Autonomous Wood-Log Grasping with a Forestry Crane: Simulator and Benchmarking
par: Vu, Minh Nhat, et autres
Publié: (2025)

Towards Transferable Defense Against Malicious Image Edits
par: Zhang, Jie, et autres
Publié: (2025)

Online Trajectory Replanner for Dynamically Grasping Irregular Objects
par: Vu, Minh Nhat, et autres
Publié: (2025)

Autonomous Catheterization with Open-source Simulator and Expert Trajectory
par: Jianu, Tudor, et autres
Publié: (2024)

ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions
par: Van Long, Phuoc Pham, et autres
Publié: (2023)

OccAny: Generalized Unconstrained Urban 3D Occupancy
par: Cao, Anh-Quan, et autres
Publié: (2026)

Biosorption of Pb 2+ From Wastewater Solution Using Material Derived From Cleistocalyx operculatus Leaves: Kinetics, Isotherms, and Thermodynamic Studies
par: Anh‐Tuan Vu, et autres
Publié: (2026)

SoVAR: Building Generalizable Scenarios from Accident Reports for Autonomous Driving Testing
par: Guo, An, et autres
Publié: (2024)

Kinetic Typography Diffusion Model
par: Park, Seonmi, et autres
Publié: (2024)

Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving
par: Zhu, Zihui, et autres
Publié: (2026)

FonTS: Text Rendering with Typography and Style Controls
par: Shi, Wenda, et autres
Publié: (2024)

Instruction Backdoor Attacks Against Customized LLMs
par: Zhang, Rui, et autres
Publié: (2024)

HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
par: Gao, Sensen, et autres
Publié: (2024)

BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance
par: Le, Huy, et autres
Publié: (2025)

Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
par: Nguyen, Quan, et autres
Publié: (2025)

Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving
par: Liu, Ming, et autres
Publié: (2025)

Toward Improving Robustness of Object Detectors Against Domain Shift
par: Tran, Le-Anh, et autres
Publié: (2023)