A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank

原文：A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank

作者：Alfredo Metere

来源：arXiv cs.DC（分布式并行）

正文

Computer Science > Cryptography and Security

arXiv:2610.33318v1 (cs)

[Submitted on 23 Oct 2026]

Title:A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank

Authors:Alfredo Metere

View a PDF of the paper titled A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank, by Alfredo Metere

View PDF

HTML (experimental)

Abstract:Large language model agents launch simulations on high-performance computing (HPC) systems, where one sbatch or mpirun can commit thousands of node-hours and a forged result can cost lives. Of 23 surveyed systems, none supervises the running job, and none holds when the control host is compromised. We fix both. Enclawed, our deterministic security runtime for AI agents, has until now served a single user; this work makes it a distributed runtime for parallel HPC and agent swarms. The Enclaweder, our hardware root of trust, keeps a compromised host from becoming a catastrophe. A launch gate decides every launch by policy alone, refusing what it cannot parse. Once the job runs, a swarm chain grants short leases against signed heartbeats and evicts on evidence, and a supervisor around every rank pauses it when its lease lapses and kills it on tampering. Each node signs with its Enclaweder’s key, so the host can forge none of it. Enclawed needs no administrator privileges and plugs into existing clusters unchanged, over Secure Shell alone. Supervision leaves the compute loop of a 16-rank LAMMPS job unchanged, on graphics processors too, and adds about 3 s of start-up. Twelve live attacks on Enclaweder-keyed ranks, colluding coordinators included, ended fail-closed. Sixteen agents on a real model attempted 24 launches that planted instructions ordered; the gate denied all 24 and allowed all 108 legitimate ones. Enclawed’s core and the HPC Agent Security Benchmark are open source.

Subjects:

Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)

Cite as:

arXiv:2610.33318 [cs.CR]

(or

arXiv:2610.33318v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2610.33318

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

安全 · 人工智能 · 分布式计算

由「前沿雷达」于 2026-10-24 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。