Random Forest Modeling for Network Intrusion Detection System

By Nabila Farnaaz, M. Jabbar. 2016

578 citations recorded by the source corpus.

Abstract With the growing usage of technology, intrusion detection became an emerging area of research. Intrusion Detection System (IDS) attempts to identify and notify the activities of users as normal (or) anomaly. IDS is a nonlinear and complicated problem and deals with network traffic data. Many IDS methods have been proposed and produce different levels of accuracy. This is why development of effective and robust Intrusion detection system is necessary. In this paper, we have built a model for intrusion detection system using random forest classifier. Random Forest (RF) is an ensemble classifier and performs well compared to other traditional classifiers for effective classification of attacks. To evaluate the performance of our model, we conducted experiments on NSL-KDD data set. Empirical result show that proposed model is efficient with low false alarm rate and high detection rate.

Subfields: Artificial Intelligence, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/6238d0720367c8dd653bd7381817af3ef236ba87

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks (2017, methodology): “RELEVANT WORK In prior studies, a number of approaches based on traditional machine learning, including SVM [10], [11], K-Nearest Neighbour (KNN) [12], ANN [13], Random Forest (RF) [14], [15] and others [16], [17], have been proposed and have achieved success for an intrusion detection system.”
Performance Comparison of Support Vector Machine, Random Forest, and Extreme Learning Machine for Intrusion Detection (2018, methodology): “[6] N. Farnaaz and M. A. Jabbar, ‘‘Random forest modeling for network intrusion detection system,’’ Proc.”
Network intrusion detection system: A systematic study of machine learning and deep learning approaches (2020, methodology): “58 Many advanced learning algorithms like Random Forest (RF) 59 and XGBoost 60 are made from multiple decision trees.”
CNN-Based Network Intrusion Detection against Denial-of-Service Attacks (2020, methodology): “[44] also use forest algorithm to build their IDS.”
CICIDS-2017 Dataset Feature Analysis With Information Gain for Anomaly Detection (2020, methodology): “Methods and measurements have been proposed that show the ability in improving detection accuracy including Chi-Square, Information Gain, Correlation Based with Naive Bayes and Decision Table Majority Classiﬁer [12], Support Vector Machine (SVM) [13] and Random Forest [12].”
A Survey of Random Forest Based Methods for Intrusion Detection Systems (2018, unknown): “Farnaaz and Jabbar (2016) propose the use of SU to select features and Random Forest as a classifier to network intrusion detection.”
Benchmarking of Machine Learning for Anomaly Based Intrusion Detection Systems in the CICIDS2017 Dataset (2021, background): “RF rec-tiﬁes this issue effectively by taking the average of multiple deep decision trees [45].”
Network Intrusion Detection Combined Hybrid Sampling With Deep Hierarchical Network (2020, methodology): “Farnaaz built a model for intrusion detection system using RF classiﬁer, the model was efﬁcient with low false alarm rate and high detection rate [13].”