Imagen de Portada

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiao, Ruochen, Xie, Shaoyuan, Yue, Justin, Sato, Takami, Wang, Lixu, Wang, Yixuan, Chen, Qi Alfred, Zhu, Qi
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective
por: Wang, Ningfei, et al.
Publicado: (2024)

Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
por: Sato, Takami, et al.
Publicado: (2023)

Compromising Embodied Agents with Contextual Backdoor Attacks
por: Liu, Aishan, et al.
Publicado: (2024)

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
por: Li, Manling, et al.
Publicado: (2024)

MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
por: Fu, Dayuan, et al.
Publicado: (2024)

Exploring Embodied Decision Making with Biomimetic Robot Touch
por: Burguete, Luke
Publicado: (2025)

Exploring the Robustness of Decision-Level Through Adversarial Attacks on LLM-Based Embodied Models
por: Liu, Shuyuan, et al.
Publicado: (2024)

Your Agent Can Defend Itself against Backdoor Attacks
por: Changjiang, Li, et al.
Publicado: (2025)

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

FlyTrap: Physical Distance-Pulling Attack Towards Camera-based Autonomous Target Tracking Systems
por: Xie, Shaoyuan, et al.
Publicado: (2025)

BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
por: Zhan, Qiusi, et al.
Publicado: (2025)

Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning
por: Liang, Wenlong, et al.
Publicado: (2025)

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
por: Zhou, Qinhong, et al.
Publicado: (2024)

CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL
por: Ni, Zhenyang, et al.
Publicado: (2026)

EmpathyAgent: Can Embodied Agents Conduct Empathetic Actions?
por: Chen, Xinyan, et al.
Publicado: (2025)

Embodied LLM Agents Learn to Cooperate in Organized Teams
por: Guo, Xudong, et al.
Publicado: (2024)

EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making
por: Lei, Zixing, et al.
Publicado: (2025)

NavTrust: Benchmarking Trustworthiness for Embodied Navigation
por: Jiang, Huaide, et al.
Publicado: (2026)

LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions, and New Attack Strategies
por: Sato, Takami, et al.
Publicado: (2023)

LLM-Enhanced Rapid-Reflex Async-Reflect Embodied Agent for Real-Time Decision-Making in Dynamically Changing Environments
por: Zheng, Yangqing, et al.
Publicado: (2025)

PFEA: An LLM-based High-Level Natural Language Planning and Feedback Embodied Agent for Human-Centered AI
por: Ding, Wenbin, et al.
Publicado: (2025)

EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
por: Ju, Ruofei, et al.
Publicado: (2026)

RescueBench: Can Embodied Agents Save Lives in the Wild ?
por: Wu, Kui, et al.
Publicado: (2026)

ManiTaskGen: A Comprehensive Task Generator for Benchmarking and Improving Vision-Language Agents on Embodied Decision-Making
por: Dai, Liu, et al.
Publicado: (2025)

Lifelong Embodied Navigation Learning
por: Wang, Xudong, et al.
Publicado: (2026)

Data-Chain Backdoor: Do You Trust Diffusion Models as Generative Data Supplier?
por: Lu, Junchi, et al.
Publicado: (2025)

Can We Trust LLM Detectors?
por: Sandhan, Jivnesh, et al.
Publicado: (2026)

Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation
por: Chen, Meng, et al.
Publicado: (2024)

Kinematics-aware Trajectory Generation and Prediction with Latent Stochastic Differential Modeling
por: Jiao, Ruochen, et al.
Publicado: (2023)

FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
por: Wang, Yucen, et al.
Publicado: (2025)

BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations
por: Monninger, Thomas, et al.
Publicado: (2026)

From Language to Action: Can LLM-Based Agents Be Used for Embodied Robot Cognition?
por: Shaji, Shinas, et al.
Publicado: (2026)

Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
por: Tan, Hengkai, et al.
Publicado: (2024)

Embodied Feeling and Reason in Decision-Making: Assessing the Somatic-Marker Hypothesis
por: Warren D. TenHouten
Publicado: (2016)

Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model
por: Zhao, Zhonghan, et al.
Publicado: (2024)

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
por: Zhang, Yang, et al.
Publicado: (2024)

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

EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents
por: Cheng, Zhili, et al.
Publicado: (2025)

Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
por: Wang, Leyao, et al.
Publicado: (2026)

Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning
por: Fan, Mingyuan, et al.
Publicado: (2025)