Image de couverture de livre

MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhu, Jinhao, Tseng, Kevin, Vernik, Gil, Huang, Xiao, Patil, Shishir G., Fang, Vivian, Popa, Raluca Ada
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Do Coding Agents Understand Least-Privilege Authorization?
par: Yan, Zheng, et autres
Publié: (2026)

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
par: Wu, Jiangrong, et autres
Publié: (2026)

MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis
par: Wang, Shenao, et autres
Publié: (2024)

Opal: Private Memory for Personal AI
par: Kaviani, Darya, et autres
Publié: (2026)

Semantic-Aware Parsing for Security Logs
par: Piet, Julien, et autres
Publié: (2025)

A Framework for Evaluating Emerging Cyberattack Capabilities of AI
par: Rodriguez, Mikel, et autres
Publié: (2025)

The Fundamental Limits of Least-Privilege Learning
par: Stadler, Theresa, et autres
Publié: (2024)

Least Privilege Access for Persistent Storage Mechanisms in Web Browsers
par: Kancherla, Gayatri Priyadarsini, et autres
Publié: (2024)

ALPS: Automated Least-Privilege Enforcement for Securing Serverless Functions
par: Shin, Changhee, et autres
Publié: (2026)

Web Agents Should Adopt the Plan-Then-Execute Paradigm
par: Piet, Julien, et autres
Publié: (2026)

Membrane: A Cryptographic Access Control System for Data Lakes
par: Kumar, Sam, et autres
Publié: (2025)

No More, No Less: Least-Privilege Language Models
par: Rauba, Paulius, et autres
Publié: (2026)

Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents
par: Uchibeke, Uchi
Publié: (2026)

Evaluating Privilege Usage of Agents with Real-World Tools
par: Zhang, Quan, et autres
Publié: (2026)

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
par: Lu, Yu-An, et autres
Publié: (2026)

Onyx: Cost-Efficient Disk-Oblivious ANN Search
par: Rathee, Deevashwer, et autres
Publié: (2026)

Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework
par: Ji, Zimo, et autres
Publié: (2026)

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

Auditing MCP Servers for Over-Privileged Tool Capabilities
par: Huang, Charoes, et autres
Publié: (2026)

PAuth - Precise Task-Scoped Authorization For Agents
par: Sharma, Reshabh K, et autres
Publié: (2026)

Progent: Securing AI Agents with Privilege Control
par: Shi, Tianneng, et autres
Publié: (2025)

AEGIS: No Tool Call Left Unchecked -- A Pre-Execution Firewall and Audit Layer for AI Agents
par: Yuan, Aojie, et autres
Publié: (2026)

ProcRoute: Process-Scoped Authorization of Split-Tunnel Routes
par: Sagayam, Arul Thileeban
Publié: (2026)

A Call to Reconsider Certification Authority Authorization (CAA)
par: Tehrani, Pouyan Fotouhi, et autres
Publié: (2024)

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents
par: Chinaei, Mohammad Hossein
Publié: (2026)

Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools
par: Mohammadi, Bardia, et autres
Publié: (2026)

The Data Enclave Advantage: A New Paradigm for Least-Privileged Data Access in a Zero-Trust World
par: Bistolfi, Nico, et autres
Publié: (2025)

Detecting Privilege Escalation with Temporal Braid Groups
par: Parisel, Christophe
Publié: (2026)

Making 'syscall' a Privilege not a Right
par: Yang, Fangfei, et autres
Publié: (2024)

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
par: Dong, Ben, et autres
Publié: (2026)

BashArena: A Control Setting for Highly Privileged AI Agents
par: Kaufman, Adam, et autres
Publié: (2025)

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
par: Probst, Benjamin, et autres
Publié: (2026)

GPUBreach: Privilege Escalation Attacks on GPUs using Rowhammer
par: Lin, Chris S., et autres
Publié: (2026)

AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent
par: Luo, Jiaqi, et autres
Publié: (2026)

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
par: Zhou, Kaiyu, et autres
Publié: (2026)

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
par: Chen, Xuan, et autres
Publié: (2026)

MPC-Minimized Secure LLM Inference
par: Rathee, Deevashwer, et autres
Publié: (2024)

Dorami: Privilege Separating Security Monitor on RISC-V TEEs
par: Kuhne, Mark, et autres
Publié: (2024)

Hybrid Privilege Escalation and Remote Code Execution Exploit Chains
par: Tulla, Miguel, et autres
Publié: (2025)

Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards
par: Normann, Philipp, et autres
Publié: (2026)