Impact of Latent Space Dimension on IoT Botnet Detection Performance: VAE-Encoder Versus ViT-Encoder

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wasswa, Hassan, Nanyonga, Aziida, Lynar, Timothy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915251767738368
author Wasswa, Hassan
Nanyonga, Aziida
Lynar, Timothy
author_facet Wasswa, Hassan
Nanyonga, Aziida
Lynar, Timothy
contents The rapid evolution of Internet of Things (IoT) technology has led to a significant increase in the number of IoT devices, applications, and services. This surge in IoT devices, along with their widespread presence, has made them a prime target for various cyber-attacks, particularly through IoT botnets. As a result, security has become a major concern within the IoT ecosystem. This study focuses on investigating how the latent dimension impacts the performance of different deep learning classifiers when trained on latent vector representations of the train dataset. The primary objective is to compare the outcomes of these models when encoder components from two cutting-edge architectures: the Vision Transformer (ViT) and the Variational Auto-Encoder (VAE) are utilized to project the high dimensional train dataset to the learned low dimensional latent space. The encoder components are employed to project high-dimensional structured .csv IoT botnet traffic datasets to various latent sizes. Evaluated on N-BaIoT and CICIoT2022 datasets, findings reveal that VAE-encoder based dimension reduction outperforms ViT-encoder based dimension reduction for both datasets in terms of four performance metrics including accuracy, precision, recall, and F1-score for all models which can be attributed to absence of spatial patterns in the datasets the ViT model attempts to learn and extract from image instances.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14879
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Impact of Latent Space Dimension on IoT Botnet Detection Performance: VAE-Encoder Versus ViT-Encoder
Wasswa, Hassan
Nanyonga, Aziida
Lynar, Timothy
Machine Learning
Artificial Intelligence
The rapid evolution of Internet of Things (IoT) technology has led to a significant increase in the number of IoT devices, applications, and services. This surge in IoT devices, along with their widespread presence, has made them a prime target for various cyber-attacks, particularly through IoT botnets. As a result, security has become a major concern within the IoT ecosystem. This study focuses on investigating how the latent dimension impacts the performance of different deep learning classifiers when trained on latent vector representations of the train dataset. The primary objective is to compare the outcomes of these models when encoder components from two cutting-edge architectures: the Vision Transformer (ViT) and the Variational Auto-Encoder (VAE) are utilized to project the high dimensional train dataset to the learned low dimensional latent space. The encoder components are employed to project high-dimensional structured .csv IoT botnet traffic datasets to various latent sizes. Evaluated on N-BaIoT and CICIoT2022 datasets, findings reveal that VAE-encoder based dimension reduction outperforms ViT-encoder based dimension reduction for both datasets in terms of four performance metrics including accuracy, precision, recall, and F1-score for all models which can be attributed to absence of spatial patterns in the datasets the ViT model attempts to learn and extract from image instances.
title Impact of Latent Space Dimension on IoT Botnet Detection Performance: VAE-Encoder Versus ViT-Encoder
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.14879