2021
DOI: 10.1155/2021/7126913
|View full text |Cite
|
Sign up to set email alerts
|

A Few‐Shot Learning‐Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data

Abstract: Network intrusion detection remains one of the major challenges in cybersecurity. In recent years, many machine-learning-based methods have been designed to capture the dynamic and complex intrusion patterns to improve the performance of intrusion detection systems. However, two issues, including imbalanced training data and new unknown attacks, still hinder the development of a reliable network intrusion detection system. In this paper, we propose a novel few-shot learning-based Siamese capsule network to tac… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 23 publications
(8 citation statements)
references
References 48 publications
0
8
0
Order By: Relevance
“…FC-Net [ 18 ] is based on RelationNet to implement few-shot traffic classification and achieves good performance in its experimental setting. DF-Net [ 23 ] takes use of siamese capsule network for AD with imbalanced traning data. A relative position mechanism and a global-enhanced feature extractor are designed in GP-Net [ 26 ] to capture the relationship between arbitrary 2-byte payload sequences.…”
Section: Resultsmentioning
confidence: 99%
“…FC-Net [ 18 ] is based on RelationNet to implement few-shot traffic classification and achieves good performance in its experimental setting. DF-Net [ 23 ] takes use of siamese capsule network for AD with imbalanced traning data. A relative position mechanism and a global-enhanced feature extractor are designed in GP-Net [ 26 ] to capture the relationship between arbitrary 2-byte payload sequences.…”
Section: Resultsmentioning
confidence: 99%
“…The model achieved 98.88% accuracy and 99.62% accuracy on different datasets. Although the model was scalable and could be applied using various algorithms, the approach ignored the worldwide spatial distance between classes, which is detrimental to the further development of recognition accuracy [22].…”
Section: Literature Reviewmentioning
confidence: 99%
“…The experimental results show that the method is universal and performs well. Wang et al [ 32 ] proposed a Siamese capsule network and an unsupervised subtype sampling scheme to solve the problem of insufficient training data of network attack traffic. Yu et al [ 33 ] utilized the Siamese network as the classification model, consisting of two two-layer CNN.…”
Section: Related Workmentioning
confidence: 99%