Metraipolis › archive › dc_d41c4d409ff1

PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact? — arXiv:2608.26882

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26882
License (as archived)
CC0-1.0
Archived
2026-10-17T14:30:15.702Z
SHA-256 of the archived text
37d062856ee0f3f6ace67060cf07fd7023e964ead302abfce7feb8dd72001201
Stable URL of this page
https://metraipolis.com/documento/dc_d41c4d409ff1

How to cite

PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact? — arXiv:2608.26882 — arXiv (en), https://arxiv.org/abs/2608.26882 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d41c4d409ff1 (Metraipolis archive dc_d41c4d409ff1, sha256 37d062856ee0f3f6ace67060cf07fd7023e964ead302abfce7feb8dd72001201)
BibTeX
@misc{dcd41c4d409ff1,
  title = {PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact? — arXiv:2608.26882},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26882},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d41c4d409ff1; sha256 37d062856ee0f3f6ace67060cf07fd7023e964ead302abfce7feb8dd72001201},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26882. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using large language model (LLM) agents represent an emerging attack threat: can an autonomous agent convert a network-reachable PLC into sustained adverse physical impact? However, existing evaluations focus on digital tasks or individual stages of PLC testing. In ICSs, evaluations that stop at software exploitation, an accepted write, or tool access may therefore mischaracterize physical risk. We present PLCBENCH, to our knowledge, the first real-PLC hardware-in-the-loop (HIL) framework for characterizing this cyber-to-physical capability and its boundaries. It combines vendor-native interaction, commercial PLC execution, closed-loop reduced-order process simulation, and independent outcome verification. A deterministic evaluator applies fixed rules to runner, communication, PLC-object, and process records to assign six hidden diagnostic flags, distinguishing usable PLC interaction, process-linked manipulation, and sustained physical impact. We instantiate PLCBENCH on four commercial PLCs crossed with four closed-loop workloads. Across five LLM families and 240 real-PLC episodes, 75 episodes (31.3%) sustain their respective physical objectives. Stagewise results show that 98 episodes stop before a valid native read, whereas 62 reach a process-linked write but do not sustain the final objective. Notably, richer process observation is associated with an increase in conditional objective attainment after a process-linked write from 44.2% to 64.0%. These measurements localize failure in configured PLC-process deployments and identify intervention points for future defense evaluation. To support reproducibility, we release the safely disclosable PLCBENCH code and a software-only reproduction pipeline through the accompanying artifact.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26882 — 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 2026-10-17T13:16:53.673Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).