Cover Image

BadRobot: Jailbreaking Embodied LLMs in the Physical World

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Hangtao, Zhu, Chenyu, Wang, Xianlong, Zhou, Ziqi, Yin, Changgan, Li, Minghui, Xue, Lulu, Wang, Yichen, Hu, Shengshan, Liu, Aishan, Guo, Peijin, Zhang, Leo Yu
Format:	Preprint
Published:	2024
Subjects:	Computers and Society Artificial Intelligence Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
by: Wang, Yichen, et al.
Published: (2025)

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
by: Zhang, Hangtao, et al.
Published: (2024)

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature
by: Wang, Yichen, et al.
Published: (2024)

Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving
by: Zhu, Zihui, et al.
Published: (2026)

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
by: Wang, Xianlong, et al.
Published: (2024)

Test-Time Backdoor Detection for Object Detection Models
by: Zhang, Hangtao, et al.
Published: (2025)

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
by: Song, Yufei, et al.
Published: (2024)

Jailbreaking Embodied LLMs via Action-level Manipulation
by: Huang, Xinyu, et al.
Published: (2026)

Beyond Model Jailbreak: Systematic Dissection of the "Ten DeadlySins" in Embodied Intelligence
by: Huang, Yuhang, et al.
Published: (2025)

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

SegTrans: Transferable Adversarial Examples for Segmentation Models
by: Song, Yufei, et al.
Published: (2025)

JailWAM: Jailbreaking World Action Models in Robot Control
by: Liu, Hanqing, et al.
Published: (2026)

BadNAVer: Exploring Jailbreak Attacks On Vision-and-Language Navigation
by: Lyu, Wenqi, et al.
Published: (2025)

dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model
by: Li, Yaxuan, et al.
Published: (2026)

Towards Reliable Forgetting: A Survey on Machine Unlearning Verification
by: Xue, Lulu, et al.
Published: (2025)

Embodied AI: From LLMs to World Models
by: Feng, Tongtong, et al.
Published: (2025)

Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation
by: Bo, Zitong, et al.
Published: (2025)

Safety Control of Service Robots with LLMs and Embodied Knowledge Graphs
by: Qi, Yong, et al.
Published: (2024)

RoboBlockly Studio: Conversational Block Programming with Embodied Robot Feedback for Computational Thinking
by: Li, Leyi, et al.
Published: (2026)

Embodied Neuromorphic Control Applied on a 7-DOF Robotic Manipulator
by: Wang, Ziqi, et al.
Published: (2025)

RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation
by: Liu, Enguang, et al.
Published: (2025)

Design and Dimensional Optimization of Legged Structures for Construction Robots
by: Liu, Xiao, et al.
Published: (2025)

Detecting and Corrupting Convolution-based Unlearnable Examples
by: Li, Minghui, et al.
Published: (2023)

Dynamic Modeling and Dimensional Optimization of Legged Mechanisms for Construction Robot
by: Liu, Xiao, et al.
Published: (2025)

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure
by: Xue, Lulu, et al.
Published: (2025)

Position: Good Embodied Reward Models Need Bad Behavior Data
by: Tian, Ran, et al.
Published: (2026)

Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training
by: Li, Yaxuan, et al.
Published: (2026)

Topology Optimization of Leg Structures for Construction Robots Based on Variable Density Method
by: Liu, Xiao, et al.
Published: (2025)

DarkFed: A Data-Free Backdoor Attack in Federated Learning
by: Li, Minghui, et al.
Published: (2024)

Embodying Physical Computing into Soft Robots
by: Wang, Jun, et al.
Published: (2025)

Multi-Agent Systems for Robotic Autonomy with LLMs
by: Chen, Junhong, et al.
Published: (2025)

A Survey: Learning Embodied Intelligence from Physical Simulators and World Models
by: Long, Xiaoxiao, et al.
Published: (2025)

Retrieval-Augmented Embodied Agents
by: Zhu, Yichen, et al.
Published: (2024)

EVA: An Embodied World Model for Future Video Anticipation
by: Chi, Xiaowei, et al.
Published: (2024)

AI or Human? Understanding Perceptions of Embodied Robots with LLMs
by: Hriscu, Lavinia, et al.
Published: (2025)

Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for Robotics
by: Abou-Chakra, Jad, et al.
Published: (2024)

The Shawshank Redemption of Embodied AI: Understanding and Benchmarking Indirect Environmental Jailbreaks
by: Li, Chunyang, et al.
Published: (2025)

HMR-1: Hierarchical Massage Robot with Vision-Language-Model for Embodied Healthcare
by: Xu, Rongtao, et al.
Published: (2026)

Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis
by: Li, Dayou, et al.
Published: (2026)