Metraipolis › archive › dc_bea172cab088

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference — arXiv:2608.15016

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15016
License (as archived)
CC0-1.0
Archived
2026-10-18T17:57:00.597Z
SHA-256 of the archived text
49a2026371c3e453496c55f0def24f36b56036a57d647a1397434c9c8b4ad7a4
Stable URL of this page
https://metraipolis.com/documento/dc_bea172cab088

How to cite

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference — arXiv:2608.15016 — arXiv (en), https://arxiv.org/abs/2608.15016 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bea172cab088 (Metraipolis archive dc_bea172cab088, sha256 49a2026371c3e453496c55f0def24f36b56036a57d647a1397434c9c8b4ad7a4)
BibTeX
@misc{dcbea172cab088,
  title = {Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference — arXiv:2608.15016},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15016},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bea172cab088; sha256 49a2026371c3e453496c55f0def24f36b56036a57d647a1397434c9c8b4ad7a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15016. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Network incident response remains slow and labor-intensive as the defender must infer multi-stage attacks from partial observations and translate recovery decisions into reliable system commands. Decision-theoretic planners provide principled optimization but typically rely on abstract states and predefined actions, while large language model (LLM) agents can reason over operational context but may hallucinate attacks and responses. Toward automating response planning, we present a hierarchical agentic response framework that integrates LLM-based attack inference, rollout planning, and digital-twin validation. A fine-tuned LLM infers the attack progression and affected hosts from security alerts and system measurements. An emulated network digital twin replays the inferred attack and returns discrepancies between predicted and observed effects to calibrate the inference. A separately fine-tuned planning agent uses the rollout planning method to prioritize affected components at the tactical layer. At the operational layer, the planning agent proposes high-level recovery actions, and an execution agent translates selected actions into recovery and verification commands that are validated in the digital twin. We evaluate the framework on a 33-component enterprise-network testbed under three multi-stage attack scenarios. The results show that our framework outperforms frontier-LLM baselines in recovery success rate by 18--31%.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15016 — 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 2026-10-18T16:29:13.978Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).