Imagen de Portada

BashArena: A Control Setting for Highly Privileged AI Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kaufman, Adam, Lucassen, James, Tracy, Tyler, Rushing, Cody, Bhatt, Aryan
Formato:	Preprint
Publicado:	2025
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

LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
por: Tracy, Tyler, et al.
Publicado: (2026)

Progent: Securing AI Agents with Privilege Control
por: Shi, Tianneng, et al.
Publicado: (2025)

Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments
por: Goel, Hardik
Publicado: (2026)

Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring
por: Schaeffer, Joachim, et al.
Publicado: (2026)

Evaluating Privilege Usage of Agents with Real-World Tools
por: Zhang, Quan, et al.
Publicado: (2026)

Do Coding Agents Understand Least-Privilege Authorization?
por: Yan, Zheng, et al.
Publicado: (2026)

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
por: Kutasov, Jonathan, et al.
Publicado: (2025)

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors
por: Najt, Elle, et al.
Publicado: (2026)

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring
por: Jotautaitė, Monika, et al.
Publicado: (2026)

MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents
por: Zhu, Jinhao, et al.
Publicado: (2025)

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
por: Probst, Benjamin, et al.
Publicado: (2026)

Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
por: Cheng, Darren, et al.
Publicado: (2026)

Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards
por: Normann, Philipp, et al.
Publicado: (2026)

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
por: Li, Changyi, et al.
Publicado: (2026)

Factor(T,U): Factored Cognition Strengthens Monitoring of Untrusted AI
por: Sandoval, Aaron, et al.
Publicado: (2025)

LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks
por: Happe, Andreas, et al.
Publicado: (2023)

Discovering Command and Control (C2) Channels on Tor and Public Networks Using Reinforcement Learning
por: Wang, Cheng, et al.
Publicado: (2024)

Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
por: Kim, Juhee, et al.
Publicado: (2025)

Securing AI Agents with Information-Flow Control
por: Costa, Manuel, et al.
Publicado: (2025)

Accelerating AI Development with Cyber Arenas
por: Cashman, William, et al.
Publicado: (2025)

Enterprise AI Must Enforce Participant-Aware Access Control
por: Bhatt, Shashank Shreedhar, et al.
Publicado: (2025)

Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks
por: Isbarov, Jafar, et al.
Publicado: (2026)

Agent Control Protocol: Admission Control for Agent Actions
por: Fernandez, Marcelo
Publicado: (2026)

MAIF: Enforcing AI Trust and Provenance with an Artifact-Centric Agentic Paradigm
por: Narajala, Vineeth Sai, et al.
Publicado: (2025)

Security of AI Agents
por: He, Yifeng, et al.
Publicado: (2024)

AgentWall: A Runtime Safety Layer for Local AI Agents
por: Aravind, Ashwin
Publicado: (2026)

AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
por: Zhang, Yixiang, et al.
Publicado: (2026)

From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming
por: Sinha, Anusha, et al.
Publicado: (2025)

LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild
por: Reworr, et al.
Publicado: (2024)

ClawLess: A Security Model of AI Agents
por: Lu, Hongyi, et al.
Publicado: (2026)

A Comparative Evaluation of AI Agent Security Guardrails
por: Li, Qi, et al.
Publicado: (2026)

AI Identity: Standards, Gaps, and Research Directions for AI Agents
por: Otsuka, Takumi, et al.
Publicado: (2026)

Multi-Agent Framework for Controllable and Protected Generative Content Creation: Addressing Copyright and Provenance in AI-Generated Media
por: Khan, Haris, et al.
Publicado: (2026)

The Hidden Dangers of Browsing AI Agents
por: Mudryi, Mykyta, et al.
Publicado: (2025)

AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
por: Zheng, Ye, et al.
Publicado: (2025)

AI-Augmented Ethical Hacking: A Practical Examination of Manual Exploitation and Privilege Escalation in Linux Environments
por: Al-Sinani, Haitham S., et al.
Publicado: (2024)

Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents
por: Narajala, Vineeth Sai, et al.
Publicado: (2025)

A Security Analysis of the OpenClaw AI Agent Framework
por: Suwansathit, Surada, et al.
Publicado: (2026)

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
por: Yang, Chenglin
Publicado: (2026)

Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
por: Motwani, Sumeet Ramesh, et al.
Publicado: (2024)