Image de couverture de livre

Propagating Unsafe Actions in LLM Controlled Multi-Robot Collaboration via Single Robot Compromise

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Zhen, Liu, Zhihuang, Luo, Mengxuan, Wu, Weishang, Cai, Zhiping
Format:	Preprint
Publié:	2026
Sujets:	Robotics Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On the Feasibility of Fingerprinting Collaborative Robot Network Traffic
par: Tang, Cheng, et autres
Publié: (2023)

Offensive Robot Cybersecurity
par: Mayoral-Vilches, Víctor
Publié: (2025)

RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents
par: Yeke, Doguhuan, et autres
Publié: (2026)

Integrating Robotic Navigation with Blockchain: A Novel PoS-Based Approach for Heterogeneous Robotic Teams
par: Paykari, Nasim, et autres
Publié: (2025)

Challenges in the Safety-Security Co-Assurance of Collaborative Industrial Robots
par: Gleirscher, Mario, et autres
Publié: (2020)

A Remote Control Painting System for Exterior Walls of High-Rise Buildings through Robotic System
par: Das, Diganta, et autres
Publié: (2024)

Cyber-Physical Steganography in Robotic Motion Control
par: Chang, Ching-Chun, et autres
Publié: (2025)

Cybersecurity and Embodiment Integrity for Modern Robots: A Conceptual Framework
par: Giaretta, Alberto, et autres
Publié: (2024)

Implementing a Robot Intrusion Prevention System (RIPS) for ROS 2
par: Soriano-Salvador, Enrique, et autres
Publié: (2024)

AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective
par: Wang, Xiaofei, et autres
Publié: (2025)

Property-Guided Cyber-Physical Reduction and Surrogation for Safety Analysis in Robotic Vehicles
par: Sayom, Nazmus Shakib, et autres
Publié: (2025)

Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks
par: Dash, Pritam, et autres
Publié: (2022)

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

Not What You Asked For: Typographic Attacks in Household Robot Manipulation
par: Iranmanesh, Ali, et autres
Publié: (2026)

Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study
par: Ward, James C., et autres
Publié: (2025)

FASR: Automated Identification of Unsafe Control Actions in STPA
par: Dardik, Ian, et autres
Publié: (2026)

RVDebloater: Mode-based Adaptive Firmware Debloating for Robotic Vehicles
par: Salehi, Mohsen, et autres
Publié: (2026)

Bayesian Methods for Trust in Collaborative Multi-Agent Autonomy
par: Hallyburton, R. Spencer, et autres
Publié: (2024)

WaveVerif: Acoustic Side-Channel based Verification of Robotic Workflows
par: Erdogan, Zeynep Yasemin, et autres
Publié: (2025)

SpecGuard: Specification Aware Recovery for Robotic Autonomous Vehicles from Physical Attacks
par: Dash, Pritam, et autres
Publié: (2024)

Supply Chain Exploitation of Secure ROS 2 Systems: A Proof-of-Concept on Autonomous Platform Compromise via Keystore Exfiltration
par: Sakib, Tahmid Hasan, et autres
Publié: (2025)

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
par: Yin, Sheng, et autres
Publié: (2024)

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

Secure Multi-hop Telemetry Broadcasts for UAV Swarm Communication
par: Rotta, Randolf, et autres
Publié: (2024)

Uncertainty-Aware 3D Position Refinement for Multi-UAV Systems
par: Alamleh, Hosam, et autres
Publié: (2026)

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

Formal Verification of Robustness and Resilience of Learning-Enabled State Estimation Systems
par: Huang, Wei, et autres
Publié: (2020)

EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling
par: Song, Zichen, et autres
Publié: (2024)

From Stealthy Data Fabrication to Unsafe Driving: Realistic Scenario Attacks on Collaborative Perception
par: Zhang, Qingzhao, et autres
Publié: (2026)

AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
par: Ying, Zonghao, et autres
Publié: (2025)

Beyond Model Jailbreak: Systematic Dissection of the "Ten DeadlySins" in Embodied Intelligence
par: Huang, Yuhang, et autres
Publié: (2025)

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search
par: Luo, Zeren, et autres
Publié: (2025)

Achieving the Safety and Security of the End-to-End AV Pipeline
par: Curran, Noah T., et autres
Publié: (2024)

Don't Trust Your Upstream: Exploiting LLM Multi-Agent System via Topology-Guided Adversarial Propagation
par: Liang, Ruichao, et autres
Publié: (2025)

Detection of Adversarial Attacks in Robotic Perception
par: Sharawy, Ziad, et autres
Publié: (2026)

ARACNE: An LLM-Based Autonomous Shell Pentesting Agent
par: Nieponice, Tomas, et autres
Publié: (2025)

NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks
par: Asl, Javad Rafiei, et autres
Publié: (2025)

Privacy Risks in Reinforcement Learning for Household Robots
par: Li, Miao, et autres
Publié: (2023)

Dynamic Deception: When Pedestrians Team Up to Fool Autonomous Cars
par: Tehrani, Masoud Jamshidiyan, et autres
Publié: (2026)

Procedimiento de auditoría de ciberseguridad para sistemas autónomos: metodología, amenazas y mitigaciones
par: Campazas-Vega, Adrián, et autres
Publié: (2025)