Metraipolis › archive › dc_fe316aeefcbe

A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank — arXiv:2610.33318

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.33318
License (as archived): CC0-1.0
Archived: 2026-10-27T07:59:40.953Z
SHA-256 of the archived text: 4784d17d53ed1f39b2a06461d7ab0f490c940ec5a3ce653cc09a381de025a36f
Stable URL of this page: https://metraipolis.com/documento/dc_fe316aeefcbe

How to cite

A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank — arXiv:2610.33318 — arXiv (en), https://arxiv.org/abs/2610.33318 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe316aeefcbe (Metraipolis archive dc_fe316aeefcbe, sha256 4784d17d53ed1f39b2a06461d7ab0f490c940ec5a3ce653cc09a381de025a36f)

BibTeX

@misc{dcfe316aeefcbe,
  title = {A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank — arXiv:2610.33318},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33318},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe316aeefcbe; sha256 4784d17d53ed1f39b2a06461d7ab0f490c940ec5a3ce653cc09a381de025a36f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33318. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2610.33318 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-27T07:55:30.819Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).