Encrypted Network Traffic Classification using Ensemble Learning Techniques

Obasi, ThankGod

doi:10.22215/etd/2020-14171

Cited by 5 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another study [47] was utilized the RF classifier and scored an accuracy of 0.893, Recall 0.890, F1 score of 0.896, and precision of 0.92. In [45] The results of this paper are also equivalent and sometimes above the results of [48,49]. One can conclude that the results of the current study are supported by other studies, however, with slight variations in some parameters.…”

Section: G Discussionsupporting

confidence: 86%

Performance Comparison of Ensemble Learning and Supervised Algorithms in Classifying Multi-label Network Traffic Flow

Machoke

Mbelwa

Agbinya

et al. 2022

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Network traffic classification is of significant importance. It helps identify network anomalies and assists in taking measures to avoid them. However, classifying network traffic correctly is a challenging task. This study aims to compare ensemble learning methods with normal supervised classification to come up with improved classification methods. Three types of network traffic were classified (Benign, Malicious, and Outliers). The data were collected experimentally by using Paessler Router Traffic Grapher software and online and were analyzed by R software. The datasets were used to train five supervised models (k-nearest neighbors, mixture discriminant analysis, Naïve Bayes, C5.0 classification model, and regularized discriminant analysis). The models were trained by 70% of the samples and the rest 30% were used for validation. The same samples were used separately in predicting individual accuracy. The results were compared to the ensemble learning models which were built with the use of the same datasets. Among the five supervised classifiers, k-nearest neighbors and C5.0 classification scored the highest accuracy of 0.868 and 0.761. The ensemble learning classifiers Bagging (Random Forest) and Boosting (eXtreme Gradient Boosting) had accuracy of 0.904 and 0.902 respectively. The results show that the ensemble learning method has higher accuracy compared to the normal supervised classifiers. Therefore, it can be used to detect malicious activities in network traffic as well as anomalies with improved accuracy.

show abstract

Section: G Discussionsupporting

confidence: 86%

Performance Comparison of Ensemble Learning and Supervised Algorithms in Classifying Multi-label Network Traffic Flow

Machoke

Mbelwa

Agbinya

et al. 2022

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

show abstract

“…Network traffic data are generated daily from various computer devices and applications connected to the internet. For example, traffic data could be contributed by users' web browsing activities, e-mails, chats, streams, file transfers, voice-over internet protocol (IP), and peer-to-peer applications [1]. These data can be captured and analysed using network or packet analysis tools.…”

Section: Introductionmentioning

confidence: 99%

An observational mechanism for detection of distributed denial-of-service attacks

Katuk

Sinal

Alsamman

et al. 2023

IJAAS

View full text Add to dashboard Cite

<span>This study proposes a continuous mechanism for detecting distributed denial of service (DDoS) attacks from network traffic data. The mechanism aims to systematically organise traffic data and prepare them for DDoS attack detection using convolutional deep-learning neural networks. The proposed mechanism contains ten phases covering activities, including data preprocessing, feature selection, data labelling, model building, model evaluation, DDoS detection, attack pattern identification, alert creation, notification delivery, and periodical data sampling. The evaluation results suggested that the detection model built based on convolutional deep-learning neural networks and relevant network traffic features provided 97.2% detection accuracy. The study designed a holistic mechanism that considers the systematic network traffic data management for continuous monitoring and good performance of DDoS attack detection. The proposed mechanism could provide a solution for network traffic data management and enhance the existing methods for DDoS attack detection. In addition, it generally contributes to the cybersecurity body of knowledge.</span>

show abstract

Performance Comparison of Different Feature Sets for Network Traffic Classification using Recursive Feature Elimination and One-Vs-Rest Random Forest Algorithms

Robbani,

Mulyana

2021

2021 15th International Conference on Telecommunication Systems, Services, and Applications (TSSA)

View full text Add to dashboard Cite

Encrypted Network Traffic Classification using Ensemble Learning Techniques

Cited by 5 publications

References 9 publications

Performance Comparison of Ensemble Learning and Supervised Algorithms in Classifying Multi-label Network Traffic Flow

Performance Comparison of Ensemble Learning and Supervised Algorithms in Classifying Multi-label Network Traffic Flow

An observational mechanism for detection of distributed denial-of-service attacks

Performance Comparison of Different Feature Sets for Network Traffic Classification using Recursive Feature Elimination and One-Vs-Rest Random Forest Algorithms

Contact Info

Product

Resources

About