Trusted AI Agents in the Cloud
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915672219451392 |
|---|---|
| author | Bodea, Teofil Misono, Masanori Pritzi, Julian Sabanic, Patrick Sommer, Thore Unnibhavi, Harshavardhan Schall, David Santos, Nuno Stavrakakis, Dimitrios Bhatotia, Pramod |
| author_facet | Bodea, Teofil Misono, Masanori Pritzi, Julian Sabanic, Patrick Sommer, Thore Unnibhavi, Harshavardhan Schall, David Santos, Nuno Stavrakakis, Dimitrios Bhatotia, Pramod |
| contents | AI agents powered by large language models are increasingly deployed as cloud services that autonomously access sensitive data, invoke external tools, and interact with other agents. However, these agents run within a complex multi-party ecosystem, where untrusted components can lead to data leakage, tampering, or unintended behavior. Existing Confidential Virtual Machines (CVMs) provide only per binary protection and offer no guarantees for cross-principal trust, accelerator-level isolation, or supervised agent behavior. We present Omega, a system that enables trusted AI agents by enforcing end-to-end isolation, establishing verifiable trust across all contributing principals, and supervising every external interaction with accountable provenance. Omega builds on Confidential VMs and Confidential GPUs to create a Trusted Agent Platform that hosts many agents within a single CVM using nested isolation. It also provides efficient multi-agent orchestration with cross-principal trust establishment via differential attestation, and a policy specification and enforcement framework that governs data access, tool usage, and inter-agent communication for data protection and regulatory compliance. Implemented on AMD SEV-SNP and NVIDIA H100, Omega fully secures agent state across CVM-GPU, and achieves high performance while enabling high-density, policy-compliant multi-agent deployments at cloud scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05951 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Trusted AI Agents in the Cloud Bodea, Teofil Misono, Masanori Pritzi, Julian Sabanic, Patrick Sommer, Thore Unnibhavi, Harshavardhan Schall, David Santos, Nuno Stavrakakis, Dimitrios Bhatotia, Pramod Cryptography and Security Artificial Intelligence Multiagent Systems AI agents powered by large language models are increasingly deployed as cloud services that autonomously access sensitive data, invoke external tools, and interact with other agents. However, these agents run within a complex multi-party ecosystem, where untrusted components can lead to data leakage, tampering, or unintended behavior. Existing Confidential Virtual Machines (CVMs) provide only per binary protection and offer no guarantees for cross-principal trust, accelerator-level isolation, or supervised agent behavior. We present Omega, a system that enables trusted AI agents by enforcing end-to-end isolation, establishing verifiable trust across all contributing principals, and supervising every external interaction with accountable provenance. Omega builds on Confidential VMs and Confidential GPUs to create a Trusted Agent Platform that hosts many agents within a single CVM using nested isolation. It also provides efficient multi-agent orchestration with cross-principal trust establishment via differential attestation, and a policy specification and enforcement framework that governs data access, tool usage, and inter-agent communication for data protection and regulatory compliance. Implemented on AMD SEV-SNP and NVIDIA H100, Omega fully secures agent state across CVM-GPU, and achieves high performance while enabling high-density, policy-compliant multi-agent deployments at cloud scale. |
| title | Trusted AI Agents in the Cloud |
| topic | Cryptography and Security Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2512.05951 |