A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam
Internet of Things (IoT) generates imbalanced network traffic; thus, the connected objects in the IoT face security issues, including different and unknown attack types. Even though traditional learning-based techniques have been used for intrusion detection in IoT, the detection of low-frequency...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2022
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/14779/1/Shapla_Khanam.pdf http://studentsrepo.um.edu.my/14779/2/Shapla_Khanam.pdf http://studentsrepo.um.edu.my/14779/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.um.stud.14779 |
|---|---|
| record_format |
eprints |
| spelling |
my.um.stud.147792024-02-17T17:55:48Z A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam Shapla , Khanam QA75 Electronic computers. Computer science T Technology (General) Internet of Things (IoT) generates imbalanced network traffic; thus, the connected objects in the IoT face security issues, including different and unknown attack types. Even though traditional learning-based techniques have been used for intrusion detection in IoT, the detection of low-frequency attacks is lacking due to the imbalanced nature of network traffic. For example, conventional learning-based techniques suffer from lower detection accuracy, higher False Positive Rate (FPR), and lower minority-class attacks detection rates. Moreover, due to the constrained nature of IoT, the conventional heavyweight intrusion detection models are not suitable for IoT. To overcome these issues, this research aims to establish and evaluate a lightweight intrusion-detection framework using Class-wise Focal Loss Variational Autoencoder (CFLVAE) for IoT. In establishing the proposed framework, a data generation model was developed using CFLVAE. Precisely, the CFLVAE model utilizes an efficient and cost-sensitive objective function called Class-wise Focal Loss (CFL) to train Variational AutoEncoder (VAE) to solve the data imbalance problem. Additionally, a highly imbalanced NSL-KDD intrusion dataset is employed to conduct extensive experimentation of the proposed model. Furthermore, a Lightweight Deep Neural Network (LDNN) model is established for intrusion detection in the IoT and trained using the balanced intrusion dataset created from the CFLVAE model to improve the intrusion detection performance. To maintain lightweight criteria, feature reduction using Mutual Information (MI) method and network compression using the Quantization technique are applied. The results demonstrate that the proposed CFLVAE with LDNN (CFLVAE-LDNN) framework obtains promising performance in generating realistic new intrusion data samples and achieves superior intrusion detection performance. Specifically, the CFLVAE-LDNN achieves 88.08% overall intrusion detection accuracy and 3.77% false positive rate. It also achieved 79.25%, and 67.5% for Root to Local (R2L) and User to Root (U2R) low-frequency attacks detection rates, respectively. More significantly, low memory and CPU time consumption confirm that the proposed model is suitable for resource-constrained IoT. Overall, the proposed model benefits researchers and practitioners with intrusion detection in IoT. 2022-08 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/14779/1/Shapla_Khanam.pdf application/pdf http://studentsrepo.um.edu.my/14779/2/Shapla_Khanam.pdf Shapla , Khanam (2022) A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam. PhD thesis, Universiti Malaya. http://studentsrepo.um.edu.my/14779/ |
| institution |
Universiti Malaya |
| building |
UM Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Malaya |
| content_source |
UM Student Repository |
| url_provider |
http://studentsrepo.um.edu.my/ |
| topic |
QA75 Electronic computers. Computer science T Technology (General) |
| spellingShingle |
QA75 Electronic computers. Computer science T Technology (General) Shapla , Khanam A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam |
| description |
Internet of Things (IoT) generates imbalanced network traffic; thus, the connected objects
in the IoT face security issues, including different and unknown attack types. Even though
traditional learning-based techniques have been used for intrusion detection in IoT, the
detection of low-frequency attacks is lacking due to the imbalanced nature of network
traffic. For example, conventional learning-based techniques suffer from lower detection
accuracy, higher False Positive Rate (FPR), and lower minority-class attacks detection rates.
Moreover, due to the constrained nature of IoT, the conventional heavyweight intrusion
detection models are not suitable for IoT. To overcome these issues, this research aims
to establish and evaluate a lightweight intrusion-detection framework using Class-wise
Focal Loss Variational Autoencoder (CFLVAE) for IoT. In establishing the proposed
framework, a data generation model was developed using CFLVAE. Precisely, the CFLVAE
model utilizes an efficient and cost-sensitive objective function called Class-wise Focal
Loss (CFL) to train Variational AutoEncoder (VAE) to solve the data imbalance problem.
Additionally, a highly imbalanced NSL-KDD intrusion dataset is employed to conduct
extensive experimentation of the proposed model. Furthermore, a Lightweight Deep
Neural Network (LDNN) model is established for intrusion detection in the IoT and
trained using the balanced intrusion dataset created from the CFLVAE model to improve
the intrusion detection performance. To maintain lightweight criteria, feature reduction
using Mutual Information (MI) method and network compression using the Quantization
technique are applied. The results demonstrate that the proposed CFLVAE with LDNN (CFLVAE-LDNN) framework obtains promising performance in generating realistic new
intrusion data samples and achieves superior intrusion detection performance. Specifically,
the CFLVAE-LDNN achieves 88.08% overall intrusion detection accuracy and 3.77%
false positive rate. It also achieved 79.25%, and 67.5% for Root to Local (R2L) and User
to Root (U2R) low-frequency attacks detection rates, respectively. More significantly,
low memory and CPU time consumption confirm that the proposed model is suitable for
resource-constrained IoT. Overall, the proposed model benefits researchers and practitioners
with intrusion detection in IoT.
|
| format |
Thesis |
| author |
Shapla , Khanam |
| author_facet |
Shapla , Khanam |
| author_sort |
Shapla , Khanam |
| title |
A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam |
| title_short |
A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam |
| title_full |
A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam |
| title_fullStr |
A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam |
| title_full_unstemmed |
A lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / Shapla Khanam |
| title_sort |
lightweight intrusion detection framework using focal loss variational autoencoder for internet of things / shapla khanam |
| publishDate |
2022 |
| url |
http://studentsrepo.um.edu.my/14779/1/Shapla_Khanam.pdf http://studentsrepo.um.edu.my/14779/2/Shapla_Khanam.pdf http://studentsrepo.um.edu.my/14779/ |
| _version_ |
1792149228096585728 |
| score |
13.211869 |