Anomaly based detection for identifying R2L (remote to local) attacks using RNN-LSTM in comparison with DNN for reducing false alarm rate

The goal of this research is to decrease the incidence of false alarms by using deep learning methods such as extended short-term memory and recurrent neural networks. It is possible to detect both local and faraway dangers using anomaly-based detection and recurrent neural networks. For this aim, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Hemasree, B., Deepa, N.
Format: Conference Proceeding
Language:English
Subjects:
Anomalies
False alarms
Power rating
Recurrent neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The goal of this research is to decrease the incidence of false alarms by using deep learning methods such as extended short-term memory and recurrent neural networks. It is possible to detect both local and faraway dangers using anomaly-based detection and recurrent neural networks. For this aim, a total of 52 samples will be utilized, with 26 samples submitted to RNN and 26 samples delivered to DNN. A G-power rating of 0.80 is obtained after comparing the two approaches. Anomaly detection effectiveness on the NSL-KDD dataset is 71% with the innovative RNN-LSTM network, compared to 58.17% with DNN. The significance level is deemed high at 0.006 (p
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0227805