Imagen de Portada

AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ying, Zonghao, Wang, Le, Xiao, Yisong, Wang, Jiakai, Ma, Yuqing, Guo, Jinyang, Yin, Zhenfei, Zhang, Mingchuan, Liu, Aishan, Liu, Xianglong
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
por: Ying, Zonghao, et al.
Publicado: (2025)

Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks
por: Ying, Zonghao, et al.
Publicado: (2024)

SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
por: Ying, Zonghao, et al.
Publicado: (2024)

Evolving Deception: When Agents Evolve, Deception Wins
por: Ying, Zonghao, et al.
Publicado: (2026)

Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw
por: Ying, Zonghao, et al.
Publicado: (2026)

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
por: Ying, Zonghao, et al.
Publicado: (2026)

RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
por: Wang, Le, et al.
Publicado: (2025)

RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents
por: Yeke, Doguhuan, et al.
Publicado: (2026)

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
por: Yin, Sheng, et al.
Publicado: (2024)

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

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
por: Ying, Zonghao, et al.
Publicado: (2025)

Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
por: Ying, Zonghao, et al.
Publicado: (2025)

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
por: Ying, Zonghao, et al.
Publicado: (2024)

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

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

Achieving the Safety and Security of the End-to-End AV Pipeline
por: Curran, Noah T., et al.
Publicado: (2024)

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
por: Li, Xiao, et al.
Publicado: (2026)

SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge
por: Ying, Zonghao, et al.
Publicado: (2025)

Property-Guided Cyber-Physical Reduction and Surrogation for Safety Analysis in Robotic Vehicles
por: Sayom, Nazmus Shakib, et al.
Publicado: (2025)

Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
por: Zou, Quanchen, et al.
Publicado: (2026)

Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI
por: Barbosa, Diego Ortiz, et al.
Publicado: (2025)

Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks
por: Xing, Wenpeng, et al.
Publicado: (2025)

DLP: towards active defense against backdoor attacks with decoupled learning process
por: Ying, Zonghao, et al.
Publicado: (2024)

NBA: defensive distillation for backdoor removal via neural behavior alignment
por: Ying, Zonghao, et al.
Publicado: (2024)

RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors
por: Bai, Fengshuo, et al.
Publicado: (2024)

Propagating Unsafe Actions in LLM Controlled Multi-Robot Collaboration via Single Robot Compromise
por: Huang, Zhen, et al.
Publicado: (2026)

Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems
por: Chen, Cheng, et al.
Publicado: (2025)

PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
por: Li, Hongwei, et al.
Publicado: (2025)

AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective
por: Wang, Xiaofei, et al.
Publicado: (2025)

Challenges in the Safety-Security Co-Assurance of Collaborative Industrial Robots
por: Gleirscher, Mario, et al.
Publicado: (2020)

CS-Eval: A Comprehensive Large Language Model Benchmark for CyberSecurity
por: Yu, Zhengmin, et al.
Publicado: (2024)

SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
por: Liu, Zhe, et al.
Publicado: (2026)

Bayesian Methods for Trust in Collaborative Multi-Agent Autonomy
por: Hallyburton, R. Spencer, et al.
Publicado: (2024)

ARACNE: An LLM-Based Autonomous Shell Pentesting Agent
por: Nieponice, Tomas, et al.
Publicado: (2025)

Not What You Asked For: Typographic Attacks in Household Robot Manipulation
por: Iranmanesh, Ali, et al.
Publicado: (2026)

Procedimiento de auditoría de ciberseguridad para sistemas autónomos: metodología, amenazas y mitigaciones
por: Campazas-Vega, Adrián, et al.
Publicado: (2025)

Channel State Information Analysis for Jamming Attack Detection in Static and Dynamic UAV Networks -- An Experimental Study
por: Mykytyn, Pavlo, et al.
Publicado: (2025)

SoK: Cybersecurity Assessment of Humanoid Ecosystem
por: Surve, Priyanka Prakash, et al.
Publicado: (2025)

Uncertainty-Aware 3D Position Refinement for Multi-UAV Systems
por: Alamleh, Hosam, et al.
Publicado: (2026)

Offensive Robot Cybersecurity
por: Mayoral-Vilches, Víctor
Publicado: (2025)