Copertina

POEX: Towards Policy Executable Jailbreak Attacks Against the LLM-based Robots

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lu, Xuancun, Huang, Zhengxian, Li, Xinfeng, Zhang, Chi, ji, Xiaoyu, Xu, Wenyuan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Robotics Artificial Intelligence Computers and Society
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks
di: Lu, Xuancun, et al.
Pubblicazione: (2025)

BadRobot: Jailbreaking Embodied LLMs in the Physical World
di: Zhang, Hangtao, et al.
Pubblicazione: (2024)

Jailbreaking LLM-Controlled Robots
di: Robey, Alexander, et al.
Pubblicazione: (2024)

Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation
di: Wang, Xianlong, et al.
Pubblicazione: (2024)

A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems
di: Zhang, Wenxiao, et al.
Pubblicazione: (2024)

Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation
di: Yin, Shiyuan, et al.
Pubblicazione: (2025)

PhantomLiDAR: Cross-modality Signal Injection Attacks against LiDAR
di: Jin, Zizhi, et al.
Pubblicazione: (2024)

VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots
di: Grigorev, Danil S., et al.
Pubblicazione: (2025)

LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions
di: Hundt, Andrew, et al.
Pubblicazione: (2024)

Virtue Ethics For Ethically Tunable Robotic Assistants
di: Ramanayake, Rajitha, et al.
Pubblicazione: (2024)

Embodied AI: Emerging Risks and Opportunities for Policy Action
di: Perlo, Jared, et al.
Pubblicazione: (2025)

Evaluating the Impact of Advanced LLM Techniques on AI-Lecture Tutors for a Robotics Course
di: Kahl, Sebastian, et al.
Pubblicazione: (2024)

A Survey on Privacy Attacks Against Digital Twin Systems in AI-Robotics
di: Fernandez, Ivan A., et al.
Pubblicazione: (2024)

Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control
di: Nakao, Mahiro, et al.
Pubblicazione: (2026)

UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
di: Zhang, Jianke, et al.
Pubblicazione: (2025)

Exploring Adversarial Robustness of LiDAR-Camera Fusion Model in Autonomous Driving
di: Yang, Bo, et al.
Pubblicazione: (2023)

Flow Policy Gradients for Robot Control
di: Yi, Brent, et al.
Pubblicazione: (2026)

Transforming Policy-Car Swerving for Mitigating Stop-and-Go Traffic Waves: A Practice-Oriented Jam-Absorption Driving Strategy
di: He, Zhengbing
Pubblicazione: (2026)

Robo-Troj: Attacking LLM-based Task Planners
di: Nahian, Mohaiminul Al, et al.
Pubblicazione: (2025)

Towards Equitable Agile Research and Development of AI and Robotics
di: Hundt, Andrew, et al.
Pubblicazione: (2024)

ImaginationPolicy: Towards Generalizable, Precise and Reliable End-to-End Policy for Robotic Manipulation
di: Lu, Dekun, et al.
Pubblicazione: (2025)

Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting
di: Zhang, Chaoyuan, et al.
Pubblicazione: (2025)

SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
di: Arachchige, Nadun Ranawaka, et al.
Pubblicazione: (2025)

An LLM-based Framework for Human-Swarm Teaming Cognition in Disaster Search and Rescue
di: Ji, Kailun, et al.
Pubblicazione: (2025)

AdaWorldPolicy: World-Model-Driven Diffusion Policy with Online Adaptive Learning for Robotic Manipulation
di: Yuan, Ge, et al.
Pubblicazione: (2026)

Model-Based AI planning and Execution Systems for Robotics
di: Wertheim, Or, et al.
Pubblicazione: (2025)

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation
di: Ying, Chenduo, et al.
Pubblicazione: (2025)

VeriGraph: Scene Graphs for Execution Verifiable Robot Planning
di: Ekpo, Daniel, et al.
Pubblicazione: (2024)

Prediction with Action: Visual Policy Learning via Joint Denoising Process
di: Guo, Yanjiang, et al.
Pubblicazione: (2024)

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
di: Zhou, Enshen, et al.
Pubblicazione: (2025)

PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?
di: Gundawar, Atharva, et al.
Pubblicazione: (2025)

Hybrid LLM-based Intelligent Framework for Robot Task Scheduling
di: Saha, Swayamjit, et al.
Pubblicazione: (2026)

Consent Chain Degradation in Embodied Multi-Agent Systems: Bridging the Gap Between AI Agent Governance and Robot Ethics
di: Haklidir, Mehmet
Pubblicazione: (2026)

A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service Robotics
di: Bode, Jonas, et al.
Pubblicazione: (2024)

CREST: Constraint-Release Execution for Multi-Robot Warehouse Shelf Rearrangement
di: Tan, Jiaqi, et al.
Pubblicazione: (2026)

Instruct2Act: From Human Instruction to Actions Sequencing and Execution via Robot Action Network for Robotic Manipulation
di: Sharma, Archit, et al.
Pubblicazione: (2026)

Studying the Effects of Robot Intervention on School Shooters in Virtual Reality
di: McClurg, Christopher A, et al.
Pubblicazione: (2025)

Efficient Continual Adaptation of Pretrained Robotic Policy with Online Meta-Learned Adapters
di: Zhu, Ruiqi, et al.
Pubblicazione: (2025)

Language-Grounded Hierarchical Planning and Execution with Multi-Robot 3D Scene Graphs
di: Strader, Jared, et al.
Pubblicazione: (2025)

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
di: Nguyen, Thanh, et al.
Pubblicazione: (2024)