2021
DOI: 10.1155/2021/5564354
|View full text |Cite
|
Sign up to set email alerts
|

I2DS: Interpretable Intrusion Detection System Using Autoencoder and Additive Tree

Abstract: Intrusion detection system (IDS), the second security gate behind the firewall, can monitor the network without affecting the network performance and ensure the system security from the internal maximum. Many researches have applied traditional machine learning models, deep learning models, or hybrid models to IDS to improve detection effect. However, according to Predicted accuracy, Descriptive accuracy, and Relevancy (PDR) framework, most of detection models based on model-based interpretability lack good de… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 8 publications
(4 citation statements)
references
References 27 publications
0
4
0
Order By: Relevance
“…Paper [25] used a characterlevel convolutional neural network (CLCNN) with exceptionally massive world-wide pooling to segment HTTP request elements and recognize them as benign or malicious requests. They evaluated the structure of the http dataset CSIC 2010 dataset and achieved an accuracy of 98.8 in 10x cross-validation, with a typical processing time per request of 2.35 ms In paper [26], they have proposed a clever interruption location framework model dependent on model based interpretability, called Interpretable Intrusion Detection System (I2DS). First and foremost, typical and assault tests are recruited via AutoEncoder (AE) with preparing tests to feature the ordinary and assault highlights, so the classifier has an exquisite impact.…”
Section: Intrusion Detection Systemmentioning
confidence: 99%
“…Paper [25] used a characterlevel convolutional neural network (CLCNN) with exceptionally massive world-wide pooling to segment HTTP request elements and recognize them as benign or malicious requests. They evaluated the structure of the http dataset CSIC 2010 dataset and achieved an accuracy of 98.8 in 10x cross-validation, with a typical processing time per request of 2.35 ms In paper [26], they have proposed a clever interruption location framework model dependent on model based interpretability, called Interpretable Intrusion Detection System (I2DS). First and foremost, typical and assault tests are recruited via AutoEncoder (AE) with preparing tests to feature the ordinary and assault highlights, so the classifier has an exquisite impact.…”
Section: Intrusion Detection Systemmentioning
confidence: 99%
“…Xu et al 28 demonstrated a model for IDS using the Interpretable IDS (I 2 DS) technique based on interpretability. Initially, the normal and attack instances were combined and reconstructed using auto encoder (AE), and it was considered a matrix of linear transformation.…”
Section: Related Workmentioning
confidence: 99%
“…Also considered were data from GPRS, NSL-KDD, and UNSW-NB15. is classifier is put up against others like Multilayer Perceptrons [28], NBTrees [29], a Random Tree ensemble [30], and Nave Bayes [31]. Study indicated that random forest-based IDSs beat other classifiers in terms of performance.…”
Section: Literature Surveymentioning
confidence: 99%