Omniscient Attacker in Stochastic Security Games with Interdependent Nodes
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918231281762304 |
|---|---|
| author | Arslantas, Yuksel Donmez, Ahmed Said Yuceel, Ege Sayin, Muhammed O. |
| author_facet | Arslantas, Yuksel Donmez, Ahmed Said Yuceel, Ege Sayin, Muhammed O. |
| contents | The adoption of reinforcement learning for critical infrastructure defense introduces a vulnerability where sophisticated attackers can strategically exploit the defense algorithm's learning dynamics. While prior work addresses this vulnerability in the context of repeated normal-form games, its extension to the stochastic games remains an open research gap. We close this gap by examining stochastic security games between an RL defender and an omniscient attacker, utilizing a tractable linear influence network model. To overcome the structural limitations of prior methods, we propose and apply neuro-dynamic programming. Our experimental results demonstrate that the omniscient attacker can significantly outperform a naive defender, highlighting the critical vulnerability introduced by the learning dynamics and the effectiveness of the proposed strategy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04561 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Omniscient Attacker in Stochastic Security Games with Interdependent Nodes Arslantas, Yuksel Donmez, Ahmed Said Yuceel, Ege Sayin, Muhammed O. Computer Science and Game Theory Systems and Control The adoption of reinforcement learning for critical infrastructure defense introduces a vulnerability where sophisticated attackers can strategically exploit the defense algorithm's learning dynamics. While prior work addresses this vulnerability in the context of repeated normal-form games, its extension to the stochastic games remains an open research gap. We close this gap by examining stochastic security games between an RL defender and an omniscient attacker, utilizing a tractable linear influence network model. To overcome the structural limitations of prior methods, we propose and apply neuro-dynamic programming. Our experimental results demonstrate that the omniscient attacker can significantly outperform a naive defender, highlighting the critical vulnerability introduced by the learning dynamics and the effectiveness of the proposed strategy. |
| title | Omniscient Attacker in Stochastic Security Games with Interdependent Nodes |
| topic | Computer Science and Game Theory Systems and Control |
| url | https://arxiv.org/abs/2512.04561 |