Metraipolis › archive › dc_1583ea69c19c

Proving the Utility of Large Language Models in Cybersecurity Simulations: A Comprehensive Examination — arXiv:2608.16422

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.16422
License (as archived): CC0-1.0
Archived: 2026-10-18T19:34:01.019Z
SHA-256 of the archived text: 11bb59d921971a553941c38edae4ba20941b967c0b3950db03f5ddbc06c618c7
Stable URL of this page: https://metraipolis.com/documento/dc_1583ea69c19c

How to cite

Proving the Utility of Large Language Models in Cybersecurity Simulations: A Comprehensive Examination — arXiv:2608.16422 — arXiv (en), https://arxiv.org/abs/2608.16422 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1583ea69c19c (Metraipolis archive dc_1583ea69c19c, sha256 11bb59d921971a553941c38edae4ba20941b967c0b3950db03f5ddbc06c618c7)

BibTeX

@misc{dc1583ea69c19c,
  title = {Proving the Utility of Large Language Models in Cybersecurity Simulations: A Comprehensive Examination — arXiv:2608.16422},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16422},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1583ea69c19c; sha256 11bb59d921971a553941c38edae4ba20941b967c0b3950db03f5ddbc06c618c7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16422. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cyber threats continue to escalate in both frequency and sophistication, necessitating more adaptive and scalable defense strategies. This paper explores how Large Language Models (LLMs) can bolster cybersecurity simulations by automating the creation of synthetic environments and identifying latent vulnerabilities. We employ YAML as a structured representation format for simulating complex network configurations, thereby enabling Large Language Model-driven pipelines to support and improve reinforcement learning (RL) agent training. Comparative studies examine the advantages of LLM-based techniques over classical approaches such as Double Q-learning with Prioritized Experience Replay (PER), emphasizing increased efficiency, higher adaptability, and enhanced realism in cyberattack simulations. In empirical benchmarks across multiple synthetic topologies, LLM-instantiated Python agents achieved up to a 94.5% compromise rate while executing in 0.02-0.06 seconds per assessment---a ~25,000x to 50,000x speedup over traditional RL training cycles. Our findings underscore the transformative potential of integrating LLMs into cybersecurity research, ultimately paving the way for more intelligent and robust cyber-defense systems.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2608.16422 — 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 2026-10-18T19:01:59.128Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).