MLTs-ADCNs: Machine Learning Techniques for Anomaly Detection in Communication Networks

Abstract

From a security perspective, the research of the jeopardized wireless communications and its expected ultra-densified ubiquitous wireless networks urge the development of a robust intrusion detection system (IDS) with powerful capabilities which could not be sufficiently provided by the existing conventional systems. IDSs are still insufficient against continuous renewable unknown attacks on the wireless communication networks, especially with the new highly vulnerable networks, leading to low accuracy and detection rate with high (false-negative, and false-positive) rates. To this end, this paper proposed a novel anomaly detection in communication networks by using an ensemble learning (EL) algorithm-based anomaly detection in communication networks (ADCNs). EL-ADCNs consist of four main stages; the first stage is the preprocessing steps. The feature selection method is the second stage. It adopts the proposed hybrid method using correlation with the random forest algorithm of ensemble learning (CFS-RF). It reduces dimensionality and retrieves the best subset feature of all the three datasets (NSL_KDD, UNSW_NB2015, and CIC_IDS2017) separately. The third stage is using hybrid EL algorithms to detect intrusions. It involves modifying two classifiers (i.e., random forest RF, and support vector machine SVM) to apply them as adaboosting and bagging EL Algorithms; using the voting average technique as the aggregation process. The final stage is testing the proposal using binary and multi-class classification forms. The experimental results of applying (30, 35, and 40) features of the proposed system to the three datasets achieved the best results of NSL_KDD are 99.6% accuracy with a 0.004 false-alarm rate, a 99.1% accuracy with a 0.008 false-alarm rate for UNSW_NB2015, and a 99.4% accuracy with a 0.0012 false-alarm rate for CIC_IDS2017.

Designing Security for the Sixth Generation: About Necessity, Concepts and Opportunities

“…Furthermore, integrity monitoring is closely related to anomaly detection, as non-legitimate sources will stand out for example in their high-level parameters (data rate, time of connection, reception angle) or the content of information. With the dynamic adaption of attackers and the expected high density of IoT devices, state-of-theart solutions for Intrusion Detection Systems (IDS) are no longer sufficient (Oleiwi, et al, 2022). Recent works have applied new combinations of different AI approaches including data preparation and feature extraction with classic machine learning algorithms (Mittal, et al, 2021) and the final step of intrusion detection with deep learning (Gupta, et al, 2022).…”

“…Especially promising is the combination of several models in an ensemble learning approach to detect anomalies (Jaw & Wang, 2021). Oleiwi et al (2022) proposed in 2022 an approach for intrusion detection with two modified classic algorithms: random forest and support vector machine, achieving an accuracy above 99 %.…”

Modified MMS: Minimization Approach for Model Subset Selection

“…The process of extracting important and relevant features from large amounts of network traffic data is a critical step in developing highly effective intrusion detection systems [23]. The high False Positive Rate (FPR) and Detection Rate (DR) are the most common problems to be treated in IDS [10], which can be effectively improved by the ensemble methods compared to conventional single classification algorithms [12]. In the ensemble process, moderately accurate components of classifiers are combined to obtain highly accurate classifiers [12].…”

“…Predictions of every subset are combined to produce the outcome. Bagging [3][4][5][6][8][9][10][11][12], Boosting [3][4][5][6]8,[10][11][12][13][14][15][16][17][18][19] are the type of homogeneous ensembles, which uses different methods to determine final prediction. Specifically, majority voting [3][4][5][6][9][10][11]17,18], weighted voting [4,6,7,9,10], average voting are prevalent methods used in existing studies.…”

Prediction of Array Antenna Assembly Accuracy Based on Auto-Encoder and Boosting-OSKELM

“…As to the problem of high-dimension, data mining technology can be used to extract valuable information [11]. The commonly used data mining method is representation reduction, which is a dimension-reducing or feature extraction method.…”