Metraipolis › archive › dc_14fa002a3dd6
DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning — arXiv:2610.40214
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40214
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:21:21.475Z
- SHA-256 of the archived text
843d692d2979e155c7b106378513a09f91391e79994cca6077446e87ea3a0188- Stable URL of this page
https://metraipolis.com/documento/dc_14fa002a3dd6
How to cite
DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning — arXiv:2610.40214 — arXiv (en), https://arxiv.org/abs/2610.40214 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_14fa002a3dd6 (Metraipolis archive dc_14fa002a3dd6, sha256 843d692d2979e155c7b106378513a09f91391e79994cca6077446e87ea3a0188)
BibTeX
@misc{dc14fa002a3dd6,
title = {DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning — arXiv:2610.40214},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40214},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_14fa002a3dd6; sha256 843d692d2979e155c7b106378513a09f91391e79994cca6077446e87ea3a0188},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40214. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As network scale and uncertainty complicate automated penetration testing, reinforcement learning (RL) environments must support controlled evaluation under defensive and non-stationary conditions. We present DYNAS (Dynamic Network Attack Simulator), which combines parameterized large-scale scenario generation with stateful intrusion detection responses, explicit scan false-positive and false-negative noise, temporary service unavailability, and duration-based action timeouts. We further introduce Pen-DHRL, a recurrent manager--worker policy that selects persistent subgoals using IDS-conditioned global context. We compare Pen-DHRL with GNN, Invariant, and Attention baselines across four scenario variants and multiple training regimes. Under IDS-disabled training followed by IDS-enabled evaluation, Pen-DHRL obtains approximately 64\% and 24\% higher reward per step on Bridge and Dynamic, respectively, and approximately 26\% and 30\% more captured hosts on VarA and VarB than the next-best baseline. With all defensive dynamics active from the beginning of training, Pen-DHRL achieves positive mean episode returns in all four scenarios, whereas the flat baselines produce negative mean returns in all 12 architecture--scenario combinations; staged curriculum training produces positive mean returns across all 16 evaluated combinations. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI). Pagina del lavoro: https://arxiv.org/abs/2610.40214 — 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 2026-11-01T02:12:13.406Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).