Cover Image

HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Zixing, Gao, Yifeng, Wang, Li, Zhao, Yunhan, Liu, Yi, Li, Jiayu, Zheng, Xiang, Wu, Zuxuan, Wang, Cong, Ma, Xingjun, Jiang, Yu-Gang
Format:	Preprint
Published:	2026
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
by: Xu, Zonghuan, et al.
Published: (2025)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
by: Li, Jiayu, et al.
Published: (2025)

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
by: Li, Xiao, et al.
Published: (2026)

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
by: Li, Qi, et al.
Published: (2026)

VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
by: Si, Shengyu, et al.
Published: (2026)

HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies
by: Du, Zhiying, et al.
Published: (2025)

LatBot: Distilling Universal Latent Actions for Vision-Language-Action Models
by: Li, Zuolei, et al.
Published: (2025)

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
by: Zhao, Yunhan, et al.
Published: (2025)

Unify Robot Actions in Camera Frame
by: Xie, Sicheng, et al.
Published: (2025)

FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
by: Wang, Xin, et al.
Published: (2025)

AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
by: Ying, Zonghao, et al.
Published: (2025)

OmniVTLA: Vision-Tactile-Language-Action Model with Semantic-Aligned Tactile Sensing
by: Cheng, Zhengxue, et al.
Published: (2025)

RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI
by: Tai, Cong, et al.
Published: (2025)

PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
by: Zheng, Yupeng, et al.
Published: (2026)

ModelLock: Locking Your Model With a Spell
by: Gao, Yifeng, et al.
Published: (2024)

RoboNurse-VLA: Robotic Scrub Nurse System based on Vision-Language-Action Model
by: Li, Shunlei, et al.
Published: (2024)

Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations
by: Zhang, Zhiyuan, et al.
Published: (2026)

Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI
by: Ni, Fei, et al.
Published: (2025)

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
by: Zhang, Borong, et al.
Published: (2025)

Passive iFIR filters for data-driven velocity control in robotics
by: Zhang, Yi, et al.
Published: (2026)

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
by: Zhao, Yunhan, et al.
Published: (2024)

Human2Robot: Learning Robot Actions from Paired Human-Robot Videos
by: Xie, Sicheng, et al.
Published: (2025)

NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
by: Zhu, Ziyue, et al.
Published: (2026)

DeRi-IGP: Learning to Manipulate Rigid Objects Using Deformable Objects via Iterative Grasp-Pull
by: Wang, Zixing, et al.
Published: (2023)

DeRi-Bot: Learning to Collaboratively Manipulate Rigid Objects via Deformable Objects
by: Wang, Zixing, et al.
Published: (2023)

Implicit Physics-aware Policy for Dynamic Manipulation of Rigid Objects via Soft Body Tools
by: Wang, Zixing, et al.
Published: (2025)

Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference
by: Liu, Yudong, et al.
Published: (2026)

Internal Safety Collapse in Frontier Large Language Models
by: Wu, Yutao, et al.
Published: (2026)

Concept-Based Dictionary Learning for Inference-Time Safety in Vision Language Action Models
by: Wen, Siqi, et al.
Published: (2026)

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
by: Zheng, Zihao, et al.
Published: (2026)

Dissipative iFIR filters for data-driven design
by: Wang, Zixing, et al.
Published: (2024)

HCSG: Human-Centric Semantic-Geometric Reasoning for Vision-Language Navigation
by: Xu, Haoxuan, et al.
Published: (2026)

VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation
by: Wang, Zhijie, et al.
Published: (2024)

HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness
by: Zheng, Zihao, et al.
Published: (2026)

ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
by: Yang, Rushuai, et al.
Published: (2026)

Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving
by: Li, Yun, et al.
Published: (2026)

TriVLA: A Triple-System-Based Unified Vision-Language-Action Model with Episodic World Modeling for General Robot Control
by: Liu, Zhenyang, et al.
Published: (2025)

SOP: A Scalable Online Post-Training System for Vision-Language-Action Models
by: Pan, Mingjie, et al.
Published: (2026)

Unified Vision-Language-Action Model
by: Wang, Yuqi, et al.
Published: (2025)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
by: Zhao, Yunhan, et al.
Published: (2026)