Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives
Fuente:
arXiv
Saved in:
| Main Author: | Son, Daeyeon |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems
by: Son, Daeyeon
Published: (2026)
by: Son, Daeyeon
Published: (2026)
An AI Agent Execution Environment to Safeguard User Data
by: Stanley, Robert, et al.
Published: (2026)
by: Stanley, Robert, et al.
Published: (2026)
Sandlock: Confining AI Agent Code with Unprivileged Linux Primitives
by: Wang, Cong, et al.
Published: (2026)
by: Wang, Cong, et al.
Published: (2026)
Secure and Efficient Access Control for Computer-Use Agents via Context Space
by: Gong, Haochen, et al.
Published: (2025)
by: Gong, Haochen, et al.
Published: (2025)
HAL 9000: a Risk Manager for ITSs
by: Freitas, Tadeu, et al.
Published: (2023)
by: Freitas, Tadeu, et al.
Published: (2023)
Guillotine: Hypervisors for Isolating Malicious AIs
by: Mickens, James, et al.
Published: (2025)
by: Mickens, James, et al.
Published: (2025)
Securing Monolithic Kernels using Compartmentalization
by: Lim, Soo Yee, et al.
Published: (2024)
by: Lim, Soo Yee, et al.
Published: (2024)
MOAT: Towards Safe BPF Kernel Extension
by: Lu, Hongyi, et al.
Published: (2023)
by: Lu, Hongyi, et al.
Published: (2023)
BULKHEAD: Secure, Scalable, and Efficient Kernel Compartmentalization with PKS
by: Guo, Yinggang, et al.
Published: (2024)
by: Guo, Yinggang, et al.
Published: (2024)
SyzParam: Introducing Runtime Parameters into Kernel Driver Fuzzing
by: Sun, Yue, et al.
Published: (2025)
by: Sun, Yue, et al.
Published: (2025)
SafeBPF: Hardware-assisted Defense-in-depth for eBPF Kernel Extensions
by: Lim, Soo Yee, et al.
Published: (2024)
by: Lim, Soo Yee, et al.
Published: (2024)
Safe Sharing of Fast Kernel-Bypass I/O Among Nontrusting Applications
by: Beadle, Alan, et al.
Published: (2025)
by: Beadle, Alan, et al.
Published: (2025)
KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
by: Yang, Chenyuan, et al.
Published: (2025)
by: Yang, Chenyuan, et al.
Published: (2025)
Analysis of Security in OS-Level Virtualization
by: Ketha, Krishna Sai, et al.
Published: (2025)
by: Ketha, Krishna Sai, et al.
Published: (2025)
Right to History: A Sovereignty Kernel for Verifiable AI Agent Execution
by: Zhang, Jing
Published: (2026)
by: Zhang, Jing
Published: (2026)
Ratio1 -- AI meta-OS
by: Damian, Andrei, et al.
Published: (2025)
by: Damian, Andrei, et al.
Published: (2025)
B-Side: Binary-Level Static System Call Identification
by: Thévenon, Gaspard, et al.
Published: (2024)
by: Thévenon, Gaspard, et al.
Published: (2024)
AgenTEE: Confidential LLM Agent Execution on Edge Devices
by: Abdollahi, Sina, et al.
Published: (2026)
by: Abdollahi, Sina, et al.
Published: (2026)
Governance-Constrained Agentic AI: Blockchain-Enforced Human Oversight for Safety-Critical Wildfire Monitoring
by: Akarma, Ali, et al.
Published: (2026)
by: Akarma, Ali, et al.
Published: (2026)
PerOS: Personalized Self-Adapting Operating Systems in the Cloud
by: Hè, Hongyu
Published: (2024)
by: Hè, Hongyu
Published: (2024)
eBPF-PATROL: Protective Agent for Threat Recognition and Overreach Limitation using eBPF in Containerized and Virtualized Environments
by: Ghimire, Sangam, et al.
Published: (2025)
by: Ghimire, Sangam, et al.
Published: (2025)
Laccolith: Hypervisor-Based Adversary Emulation with Anti-Detection
by: Orbinato, Vittorio, et al.
Published: (2023)
by: Orbinato, Vittorio, et al.
Published: (2023)
Rethinking Provenance Completeness with a Learning-Based Linux Scheduler
by: Mao, Jinsong, et al.
Published: (2025)
by: Mao, Jinsong, et al.
Published: (2025)
A Survey of Operating System Kernel Fuzzing
by: Xu, Jiacheng, et al.
Published: (2025)
by: Xu, Jiacheng, et al.
Published: (2025)
WebAssembly Based Portable and Secure Sensor Interface for Internet of Things
by: Ou, Botong, et al.
Published: (2026)
by: Ou, Botong, et al.
Published: (2026)
NecoFuzz: Effective Fuzzing of Nested Virtualization via Fuzz-Harness Virtual Machines
by: Ishii, Reima, et al.
Published: (2025)
by: Ishii, Reima, et al.
Published: (2025)
Agent Name Service (ANS): A Proof-of-Concept Trust Layer for Secure AI Agent Discovery, Identity, and Governance in Kubernetes
by: Mittal, Akshay, et al.
Published: (2026)
by: Mittal, Akshay, et al.
Published: (2026)
When eBPF Meets Machine Learning: On-the-fly OS Kernel Compartmentalization
by: Wang, Zicheng, et al.
Published: (2024)
by: Wang, Zicheng, et al.
Published: (2024)
OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access
by: Zhu, Genliang, et al.
Published: (2026)
by: Zhu, Genliang, et al.
Published: (2026)
Sharing is caring: Attestable and Trusted Workflows out of Distrustful Components
by: Sadi, Amir Al, et al.
Published: (2026)
by: Sadi, Amir Al, et al.
Published: (2026)
OAMAC: Origin-Aware Mandatory Access Control for Practical Post-Compromise Attack Surface Reduction
by: Mohammed, Omer Abdelmajeed Idris, et al.
Published: (2026)
by: Mohammed, Omer Abdelmajeed Idris, et al.
Published: (2026)
Evolution of Android's Permission-based Security Model and Challenges
by: Solanki, Rajendra Kumar, et al.
Published: (2026)
by: Solanki, Rajendra Kumar, et al.
Published: (2026)
Ringmaster: How to juggle high-throughput host OS system calls from TrustZone TEEs
by: Habeeb, Richard, et al.
Published: (2026)
by: Habeeb, Richard, et al.
Published: (2026)
Tock: From Research to Securing 10 Million Computers
by: Schuermann, Leon, et al.
Published: (2026)
by: Schuermann, Leon, et al.
Published: (2026)
Contextualizing Security and Privacy of Software-Defined Vehicles: A Literature Review and Industry Perspectives
by: De Vincenzi, Marco, et al.
Published: (2024)
by: De Vincenzi, Marco, et al.
Published: (2024)
Plug. Play. Persist. Inside a Ready-to-Go Havoc C2 Infrastructure
by: Di Santo, Alessio
Published: (2025)
by: Di Santo, Alessio
Published: (2025)
SoK: Software Compartmentalization
by: Lefeuvre, Hugo, et al.
Published: (2024)
by: Lefeuvre, Hugo, et al.
Published: (2024)
The Android Platform Security Model (2023)
by: Mayrhofer, René, et al.
Published: (2019)
by: Mayrhofer, René, et al.
Published: (2019)
CAEC: Confidential, Attestable, and Efficient Inter-CVM Communication with Arm CCA
by: Abdollahi, Sina, et al.
Published: (2025)
by: Abdollahi, Sina, et al.
Published: (2025)
Case Study: Securing MMU-less Linux Using CHERI
by: Almatary, Hesham, et al.
Published: (2023)
by: Almatary, Hesham, et al.
Published: (2023)
Similar Items
-
ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems
by: Son, Daeyeon
Published: (2026) -
An AI Agent Execution Environment to Safeguard User Data
by: Stanley, Robert, et al.
Published: (2026) -
Sandlock: Confining AI Agent Code with Unprivileged Linux Primitives
by: Wang, Cong, et al.
Published: (2026) -
Secure and Efficient Access Control for Computer-Use Agents via Context Space
by: Gong, Haochen, et al.
Published: (2025) -
HAL 9000: a Risk Manager for ITSs
by: Freitas, Tadeu, et al.
Published: (2023)