Trustworthy Intrusion Detection: Confidence Estimation Using Latent Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pitsiorlas, Ioannis, Arvanitakis, George, Kountouris, Marios
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912039316750336
author Pitsiorlas, Ioannis
Arvanitakis, George
Kountouris, Marios
author_facet Pitsiorlas, Ioannis
Arvanitakis, George
Kountouris, Marios
contents This work introduces a novel method for enhancing confidence in anomaly detection in Intrusion Detection Systems (IDS) through the use of a Variational Autoencoder (VAE) architecture. By developing a confidence metric derived from latent space representations, we aim to improve the reliability of IDS predictions against cyberattacks. Applied to the NSL-KDD dataset, our approach focuses on binary classification tasks to effectively distinguish between normal and malicious network activities. The methodology demonstrates a significant enhancement in anomaly detection, evidenced by a notable correlation of 0.45 between the reconstruction error and the proposed metric. Our findings highlight the potential of employing VAEs for more accurate and trustworthy anomaly detection in network security.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13774
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Trustworthy Intrusion Detection: Confidence Estimation Using Latent Space
Pitsiorlas, Ioannis
Arvanitakis, George
Kountouris, Marios
Cryptography and Security
Artificial Intelligence
Machine Learning
This work introduces a novel method for enhancing confidence in anomaly detection in Intrusion Detection Systems (IDS) through the use of a Variational Autoencoder (VAE) architecture. By developing a confidence metric derived from latent space representations, we aim to improve the reliability of IDS predictions against cyberattacks. Applied to the NSL-KDD dataset, our approach focuses on binary classification tasks to effectively distinguish between normal and malicious network activities. The methodology demonstrates a significant enhancement in anomaly detection, evidenced by a notable correlation of 0.45 between the reconstruction error and the proposed metric. Our findings highlight the potential of employing VAEs for more accurate and trustworthy anomaly detection in network security.
title Trustworthy Intrusion Detection: Confidence Estimation Using Latent Space
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2409.13774