2020
DOI: 10.3390/info11050243
|View full text |Cite
|
Sign up to set email alerts
|

Using a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) to Classify Network Attacks

Abstract: An intrusion detection system (IDS) identifies whether the network traffic behavior is normal or abnormal or identifies the attack types. Recently, deep learning has emerged as a successful approach in IDSs, having a high accuracy rate with its distinctive learning mechanism. In this research, we developed a new method for intrusion detection to classify the NSL-KDD dataset by combining a genetic algorithm (GA) for optimal feature selection and long short-term memory (LSTM) with a recurrent neural network (RNN… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
17
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
4
1

Relationship

0
10

Authors

Journals

citations
Cited by 83 publications
(27 citation statements)
references
References 21 publications
0
17
0
1
Order By: Relevance
“…If the recorded information is no longer needed, forget gates can be used to reset the state of the linear unit. Simple sigmoid threshold units are used in these gates [30].…”
Section: Long Short Term Memory Methodsmentioning
confidence: 99%
“…If the recorded information is no longer needed, forget gates can be used to reset the state of the linear unit. Simple sigmoid threshold units are used in these gates [30].…”
Section: Long Short Term Memory Methodsmentioning
confidence: 99%
“…This heterogeneous ensemble learning ensured that the model has better adaptability and accuracy when compared with other methods. The study by Muhuri et al [160] shows that the performance of the LSTM-RNN model is better in binary classification as compared to multiclass classification. In binary classification, the proposed model outperforms SVM and RF models.…”
Section: Review Of Various Deep Learning Techniques In Idsmentioning
confidence: 99%
“…The machine learning models for forecasting consists of a wide range of techniques-from the conventional forecasting methodologies such as ARIMA [18,19] and Exponential smoothing to newer deep learning approaches such as LSTM [20]. It is no surprise that it can become very challenging to apply several regression techniques over time-series data-as the time-series data tend to have sparse values, so they shelter larger contributions to randomness than the seasonality of the data.…”
Section: Executionmentioning
confidence: 99%