Image de couverture de livre

From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xie, Mingyang, Wei-Kocsis, Jin
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems
par: Zhang, Wenxiao, et autres
Publié: (2024)

From Prompt to Physical Actuation: Holistic Threat Modeling of LLM-Enabled Robotic Systems
par: Nagaraja, Neha, et autres
Publié: (2026)

DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
par: Xu, Zonghuan, et autres
Publié: (2025)

Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation
par: Wang, Xianlong, et autres
Publié: (2024)

When Attention Betrays: Erasing Backdoor Attacks in Robotic Policies by Reconstructing Visual Tokens
par: Li, Xuetao, et autres
Publié: (2026)

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models
par: Xu, Bingxin, et autres
Publié: (2026)

ComFree-Sim: A GPU-Parallelized Analytical Contact Physics Engine for Scalable Contact-Rich Robotics Simulation and Control
par: Borse, Chetan, et autres
Publié: (2026)

From Language to Action: Can LLM-Based Agents Be Used for Embodied Robot Cognition?
par: Shaji, Shinas, et autres
Publié: (2026)

From Scanning Guidelines to Action: A Robotic Ultrasound Agent with LLM-Based Reasoning
par: Bi, Yuan, et autres
Publié: (2026)

Trojan Attacks on Neural Network Controllers for Robotic Systems
par: Younesi, Farbod, et autres
Publié: (2026)

ActionReasoning: Robot Action Reasoning in 3D Space with LLM for Robotic Brick Stacking
par: Wang, Guangming, et autres
Publié: (2026)

Toward Deployable Multi-Robot Collaboration via a Symbolically-Guided Decision Transformer
par: Rasanji, Rathnam Vidushika, et autres
Publié: (2025)

Propagating Unsafe Actions in LLM Controlled Multi-Robot Collaboration via Single Robot Compromise
par: Huang, Zhen, et autres
Publié: (2026)

Nautilus: From One Prompt to Plug-and-Play Robot Learning
par: Jin, Yufeng, et autres
Publié: (2026)

Adversarial Attacks on Robotic Vision Language Action Models
par: Jones, Eliot Krzysztof, et autres
Publié: (2025)

From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control
par: Shentu, Yide, et autres
Publié: (2024)

JailWAM: Jailbreaking World Action Models in Robot Control
par: Liu, Hanqing, et autres
Publié: (2026)

REFLEX: Metacognitive Reasoning for Reflective Zero-Shot Robotic Planning with Large Language Models
par: Lin, Wenjie, et autres
Publié: (2025)

Hierarchical Prompting with Dual LLM Modules for Robotic Task and Motion Planning
par: Źróbek, Karolina, et autres
Publié: (2026)

CrayonRobo: Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation
par: Li, Xiaoqi, et autres
Publié: (2025)

MotuBrain: An Advanced World Action Model for Robot Control
par: MotuBrain Team, et autres
Publié: (2026)

Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation
par: Tan, Huajie, et autres
Publié: (2026)

Reducing Mental Workload through On-Demand Human Assistance for Physical Action Failures in LLM-based Multi-Robot Coordination
par: Hasegawa, Shoichi, et autres
Publié: (2026)

LA-RCS: LLM-Agent-Based Robot Control System
par: Park, TaekHyun, et autres
Publié: (2025)

Human2Robot: Learning Robot Actions from Paired Human-Robot Videos
par: Xie, Sicheng, et autres
Publié: (2025)

Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
par: Rathbun, Ethan, et autres
Publié: (2026)

RoboNurse-VLA: Robotic Scrub Nurse System based on Vision-Language-Action Model
par: Li, Shunlei, et autres
Publié: (2024)

Unify Robot Actions in Camera Frame
par: Xie, Sicheng, et autres
Publié: (2025)

Pre-Execution Safety Gate & Task Safety Contracts for LLM-Controlled Robot Systems
par: Obi, Ike, et autres
Publié: (2026)

exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation
par: Xu, Yue, et autres
Publié: (2025)

Inject Once Survive Later: Backdooring Vision-Language-Action Models to Persist Through Downstream Fine-tuning
par: Zhou, Jianyi, et autres
Publié: (2026)

FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models
par: An, Xinyuan, et autres
Publié: (2026)

Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning
par: Lee, I, et autres
Publié: (2024)

Jailbreaking LLM-Controlled Robots
par: Robey, Alexander, et autres
Publié: (2024)

When Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning
par: Huang, Tairan, et autres
Publié: (2026)

Language-Grounded Decoupled Action Representation for Robotic Manipulation
par: Weng, Wuding, et autres
Publié: (2026)

Intelligent Robotic Control System Based on Computer Vision Technology
par: Che, Chang, et autres
Publié: (2024)

Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations
par: Zhang, Yuchi, et autres
Publié: (2025)

Unified Learning of Temporal Task Structure and Action Timing for Bimanual Robot Manipulation
par: Dreher, Christian, et autres
Publié: (2026)

Instruct2Act: From Human Instruction to Actions Sequencing and Execution via Robot Action Network for Robotic Manipulation
par: Sharma, Archit, et autres
Publié: (2026)