Empirical Evaluation of Noise Influence on Supervised Machine Learning Algorithms Using Intrusion Detection Datasets

Al-Gethami, Khalid M.; Al-Akhras, Mousa; Alawairdhi, Mohammed

doi:10.1155/2021/8836057

Cited by 19 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Anomaly detection is a very important branch of machine learning, with a wide range of practical applications, and it aims to detect special points in data. It is suitable for fault diagnosis [1,2], system health monitoring [3], network security detection [4], intrusion and fraud detection [5][6][7], measurement, and other fields. e exceptions to the normal instances are called anomalies, so anomalies are also called exceptions, outliers, novelties, noises, and deviations [8].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Anomaly Detection Based on Deep Autoencoding and Clustering

Zhang

Liu

Chen

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

The unsupervised anomaly detection task based on high-dimensional or multidimensional data occupies a very important position in the field of machine learning and industrial applications; especially in the aspect of network security, the anomaly detection of network data is particularly important. The key to anomaly detection is density estimation. Although the methods of dimension reduction and density estimation have made great progress in recent years, most dimension reduction methods are difficult to retain the key information of original data or multidimensional data. Recent studies have shown that the deep autoencoder (DAE) can solve this problem well. In order to improve the performance of unsupervised anomaly detection, we propose an anomaly detection scheme based on a deep autoencoder (DAE) and clustering methods. The deep autoencoder is trained to learn the compressed representation of the input data and then feed it to clustering approach. This scheme makes full use of the advantages of the deep autoencoder (DAE) to generate low-dimensional representation and reconstruction errors for the input high-dimensional or multidimensional data and uses them to reconstruct the input samples. The proposed scheme could eliminate redundant information contained in the data, improve performance of clustering methods in identifying abnormal samples, and reduce the amount of calculation. To verify the effectiveness of the proposed scheme, massive comparison experiments have been conducted with traditional dimension reduction algorithms and clustering methods. The results of experiments demonstrate that, in most cases, the proposed scheme outperforms the traditional dimension reduction algorithms with different clustering methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Anomaly Detection Based on Deep Autoencoding and Clustering

Zhang

Liu

Chen

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…However, there are specific challenges associated with dataset quality in SDN that need to be addressed for effective ML-based solutions [134,135].…”

Section: Datasets Qualitymentioning

confidence: 99%

Machine-Learning-Based Traffic Classification in Software-Defined Networks

Serag,

Abdalzaher,

Elsayed

et al. 2024

Electronics

View full text Add to dashboard Cite

Many research efforts have gone into upgrading antiquated communication network infrastructures with better ones to support contemporary services and applications. Smart networks can adapt to new technologies and traffic trends on their own. Software-defined networking (SDN) separates the control plane from the data plane and runs programs in one place, changing network management. New technologies like SDN and machine learning (ML) could improve network performance and QoS. This paper presents a comprehensive research study on integrating SDN with ML to improve network performance and quality-of-service (QoS). The study primarily investigates ML classification methods, highlighting their significance in the context of traffic classification (TC). Additionally, traditional methods are discussed to clarify the ML outperformance observed throughout our investigation, underscoring the superiority of ML algorithms in SDN TC. The study describes how labeled traffic data can be used to train ML models for appropriately classifying SDN TC flows. It examines the pros and downsides of dynamic and adaptive TC using ML algorithms. The research also examines how ML may improve SDN security. It explores using ML for anomaly detection, intrusion detection, and attack mitigation in SDN networks, stressing the proactive threat-detection and response benefits. Finally, we discuss the SDN-ML QoS integration problems and research gaps. Furthermore, scalability and performance issues in large-scale SDN implementations are identified as potential issues and areas for additional research.

show abstract

“…Monitoring the energy consumption on 6LowPAN to detect unusual traffic is one of methods to detect DDoS attacks successfully [59]. Machine learning algorithms are also widely used for DDoS detection and simple supervised learning algorithms such as random forests may provide adequate results [60,61]. Deep learning architectures have been the latest focus area in the intrusion detection research since they offer high accuracy and generality [62].…”

Section: Ddos Attackmentioning

confidence: 99%

A Survey on Security Attacks with Remote Ground Robots

Özdol¹,

Köseler²,

Alçiçek³

et al. 2021

El-Cezeri Fen Ve Mühendislik Dergisi

View full text Add to dashboard Cite

Contemporary healthcare systems contain diverse computing devices that construct very complex systems to manage patients' data more efficiently. Connected computing devices, such as the Internet of Things (IoT) that may have limited processing powers, have contributed more than ever with the advent of wearable body area networks (WBAN). These devices are connected to other medical devices to share sensitive health data with corresponding entities like hospitals, research institutions, and insurance companies. Since health data are very sensitive, they should be always available to authorized entities and unavailable to other entities. Moreover, COVID-19 pandemic has added additional value to health data which case increases cyber-attacks on (Electronic health) E-health systems with different tools dramatically. In this paper, several cyber-attacks on Ehealth systems are explored. Particularly, we have focused on attacks to IoT based wearable health devices for body area networks. The paper contains the architecture of wearable health devices to show the potential attack surface. One of the main contributions of the paper is to present cyber-attacks on wearable e-health devices with ground robots. A tactical ground robot is portable devices that may be used to carry out several cyber-attacks on E-health systems. Moreover, the paper contains analyses of the attacks with ground robots.

show abstract

Empirical Evaluation of Noise Influence on Supervised Machine Learning Algorithms Using Intrusion Detection Datasets

Cited by 19 publications

References 35 publications

Unsupervised Anomaly Detection Based on Deep Autoencoding and Clustering

Unsupervised Anomaly Detection Based on Deep Autoencoding and Clustering

Machine-Learning-Based Traffic Classification in Software-Defined Networks

A Survey on Security Attacks with Remote Ground Robots

Contact Info

Product

Resources

About