An Empirical Game-Theoretic Analysis of Autonomous Cyber-Defence Agents

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Palmer, Gregory, Swaby, Luke, Harrold, Daniel J. B., Stewart, Matthew, Hiles, Alex, Willis, Chris, Miles, Ian, Farmer, Sara
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916592393125888
author Palmer, Gregory
Swaby, Luke
Harrold, Daniel J. B.
Stewart, Matthew
Hiles, Alex
Willis, Chris
Miles, Ian
Farmer, Sara
author_facet Palmer, Gregory
Swaby, Luke
Harrold, Daniel J. B.
Stewart, Matthew
Hiles, Alex
Willis, Chris
Miles, Ian
Farmer, Sara
contents The recent rise in increasingly sophisticated cyber-attacks raises the need for robust and resilient autonomous cyber-defence (ACD) agents. Given the variety of cyber-attack tactics, techniques and procedures (TTPs) employed, learning approaches that can return generalisable policies are desirable. Meanwhile, the assurance of ACD agents remains an open challenge. We address both challenges via an empirical game-theoretic analysis of deep reinforcement learning (DRL) approaches for ACD using the principled double oracle (DO) algorithm. This algorithm relies on adversaries iteratively learning (approximate) best responses against each others' policies; a computationally expensive endeavour for autonomous cyber operations agents. In this work we introduce and evaluate a theoretically-sound, potential-based reward shaping approach to expedite this process. In addition, given the increasing number of open-source ACD-DRL approaches, we extend the DO formulation to allow for multiple response oracles (MRO), providing a framework for a holistic evaluation of ACD approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2501_19206
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Empirical Game-Theoretic Analysis of Autonomous Cyber-Defence Agents
Palmer, Gregory
Swaby, Luke
Harrold, Daniel J. B.
Stewart, Matthew
Hiles, Alex
Willis, Chris
Miles, Ian
Farmer, Sara
Artificial Intelligence
Cryptography and Security
Computer Science and Game Theory
The recent rise in increasingly sophisticated cyber-attacks raises the need for robust and resilient autonomous cyber-defence (ACD) agents. Given the variety of cyber-attack tactics, techniques and procedures (TTPs) employed, learning approaches that can return generalisable policies are desirable. Meanwhile, the assurance of ACD agents remains an open challenge. We address both challenges via an empirical game-theoretic analysis of deep reinforcement learning (DRL) approaches for ACD using the principled double oracle (DO) algorithm. This algorithm relies on adversaries iteratively learning (approximate) best responses against each others' policies; a computationally expensive endeavour for autonomous cyber operations agents. In this work we introduce and evaluate a theoretically-sound, potential-based reward shaping approach to expedite this process. In addition, given the increasing number of open-source ACD-DRL approaches, we extend the DO formulation to allow for multiple response oracles (MRO), providing a framework for a holistic evaluation of ACD approaches.
title An Empirical Game-Theoretic Analysis of Autonomous Cyber-Defence Agents
topic Artificial Intelligence
Cryptography and Security
Computer Science and Game Theory
url https://arxiv.org/abs/2501.19206