Deep Generative Models to Extend Active Directory Graphs with Honeypot Users

Ondřej Lukáš, Sebastian Garcia

2021

Abstract

Active Directory (AD) is a crucial element of large organizations, given its central role in managing access to resources. Since AD is used by all users in the organization, it is hard to detect attackers. We propose to generate and place fake users (honeyusers) in AD structures to help detect attacks. However, not any honeyuser will attract attackers. Our method generates honeyusers with a Variational Autoencoder that enriches the AD structure with well-positioned honeyusers. It first learns the embeddings of the original nodes and edges in the AD, then it uses a modified Bidirectional DAG-RNN to encode the parameters of the probability distribution of the latent space of node representations. Finally, it samples nodes from this distribution and uses an MLP to decide where the nodes are connected. The model was evaluated by the similarity of the generated AD with the original, by the positions of the new nodes, by the similarity with GraphRNN and finally by making real intruders attack the generated AD structure to see if they select the honeyusers. Results show that our machine learning model is good enough to generate well-placed honeyusers for existing AD structures so that intruders are lured into them.

Paper Citation

in Harvard Style

Lukáš O. and Garcia S. (2021). Deep Generative Models to Extend Active Directory Graphs with Honeypot Users. In Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA, ISBN 978-989-758-526-5, pages 140-147. DOI: 10.5220/0010556601400147

in Bibtex Style

@conference{delta21,
author={Ondřej Lukáš and Sebastian Garcia},
title={Deep Generative Models to Extend Active Directory Graphs with Honeypot Users},
booktitle={Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,},
year={2021},
pages={140-147},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010556601400147},
isbn={978-989-758-526-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,
TI - Deep Generative Models to Extend Active Directory Graphs with Honeypot Users
SN - 978-989-758-526-5
AU - Lukáš O.
AU - Garcia S.
PY - 2021
SP - 140
EP - 147
DO - 10.5220/0010556601400147