CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Emerson, Harry, Bates, Liz, Hicks, Chris, Mavroudis, Vasilios
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929553930190848
author Emerson, Harry
Bates, Liz
Hicks, Chris
Mavroudis, Vasilios
author_facet Emerson, Harry
Bates, Liz
Hicks, Chris
Mavroudis, Vasilios
contents CybORG++ is an advanced toolkit for reinforcement learning research focused on network defence. Building on the CAGE 2 CybORG environment, it introduces key improvements, including enhanced debugging capabilities, refined agent implementation support, and a streamlined environment that enables faster training and easier customisation. Along with addressing several software bugs from its predecessor, CybORG++ introduces MiniCAGE, a lightweight version of CAGE 2, which improves performance dramatically, up to 1000x faster execution in parallel iterations, without sacrificing accuracy or core functionality. CybORG++ serves as a robust platform for developing and evaluating defensive agents, making it a valuable resource for advancing enterprise network defence research.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16324
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents
Emerson, Harry
Bates, Liz
Hicks, Chris
Mavroudis, Vasilios
Cryptography and Security
Artificial Intelligence
CybORG++ is an advanced toolkit for reinforcement learning research focused on network defence. Building on the CAGE 2 CybORG environment, it introduces key improvements, including enhanced debugging capabilities, refined agent implementation support, and a streamlined environment that enables faster training and easier customisation. Along with addressing several software bugs from its predecessor, CybORG++ introduces MiniCAGE, a lightweight version of CAGE 2, which improves performance dramatically, up to 1000x faster execution in parallel iterations, without sacrificing accuracy or core functionality. CybORG++ serves as a robust platform for developing and evaluating defensive agents, making it a valuable resource for advancing enterprise network defence research.
title CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2410.16324