A two-stage stacked ensemble intrusion detection system using five base classifiers and MLP with optimal feature selection

Mushtaq, Earum; Zameer, Aneela; Khan, Asifullah

doi:10.1016/j.micpro.2022.104660

Cited by 17 publications

(13 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [108] improved intrusion detection by using a two-level classifier in conjunction with a hybrid feature selection technique. To identify the faulty WSN nodes, the traffic data was analyzed using SVM and MLP algorithms.…”

Section: A Intrusion Detectionmentioning

confidence: 99%

“…Due to the lack of a central location for ML training within this particular network architecture and the sharing of CPU and power resources of all embedded devices, this location becomes indispensable for the deployment of ML. In a significant part of the research studies on ML techniques [108], there is a need for more clarity on the specific implementation of these algorithms in WSNs. The proper educational context for training these methods remains unclear, as extensive previous research has facilitated the identification of attacks and faulty nodes [101].…”

Section: Open Issues a Location Of The ML Training Processmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Solutions for the Security of Wireless Sensor Networks: A Review

Ghadi,

Mazhar,

Shloul

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Energy efficiency and safety are two essential factors that play a significant role in operating a wireless sensor network. However, it is claimed that these two factors are naturally conflicting. The level of electrical consumption required by a security system is directly proportional to its degree of complexity. Wireless sensor networks require additional security measures above the capabilities of conventional network security protocols, such as encryption and key management. The potential application of machine learning techniques to address network security concerns is frequently discussed. These devices will have complete artificial intelligence capabilities, enabling them to understand their environment and respond. During the training phase, machine-learning systems may face challenges due to the large amount of data required and the complex nature of the training procedure. This article focuses on machine learning algorithms used to solve the security issues of wireless sensor networks. This article also focuses on different types of attacks on layers of the wireless sensor network. Moreover, this study addresses several unsolved issues, including adapting machine learning algorithms to accommodate the sensors' functionalities in this network configuration. Furthermore, this article also focuses on open issues in this field that must be solved.

show abstract

Section: A Intrusion Detectionmentioning

confidence: 99%

Section: Open Issues a Location Of The ML Training Processmentioning

confidence: 99%

Machine Learning Solutions for the Security of Wireless Sensor Networks: A Review

Ghadi,

Mazhar,

Shloul

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The results showed that the proposed IDS system reduced the false positive rate and improved detection accuracy. Mushtaq et al [59] offer a stacked ensemble-based intrusion detection system (SE-IDS) that uses optimum feature selection to increase detection accuracy and decrease false positives. As foundation learners, the system contains a Decision Tree (DT), XGBoost, bagging classifier, additional tree, RF, and an MLP as a meta-learner.…”

Section: Literature Reviewmentioning

confidence: 99%

Overcoming the Challenges of Data Lack, Leakage, and Dimensionality in Intrusion Detection Systems: A Comprehensive Review

Bouke,

Abdullah,

Udzir

et al. 2024

JCIS

View full text Add to dashboard Cite

The Internet of Things (IoT) and cloud computing are rapidly gaining momentum as decentralized internet-based technologies and have led to an increase in information in nearly every technical and commercial industry. However, ensuring the security of IoT systems is a pressing issue due to the complexities involved in connected and shared environments. Networks are guarded by Intrusion Detection Systems (IDS) against various cyber threats such as malware, viruses, and unauthorized access. IDS have recently adopted Machine Learning (ML) and Deep Learning (DL) techniques to identify and classify security risks. However, the effective utilization of these technologies depends on the availability, quality, and characteristics of the data used to train models. Moreover, data lack, data leak, and dimensionality (DLLD) are common problems in data science and ML. This paper surveys existing research and suggests solutions for overcoming DLLD-related issues to improve IDS model.

show abstract

“…Host-based IDS and Network-based IDS are the primary categories of IDS, where signature-based and anomalybased are the detection methods of IDS [2]. Signature-based IDS depends on predefined patterns or signatures of known attacks and compares network traffic against these known signatures to detect potential threats [3]. Anomaly-based IDS uses statistical or Machine Learning (ML) approaches to establish the baseline behavior of normal and deviations of the threats [2].…”

Section: Introductionmentioning

confidence: 99%

“…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.…”

Section: Introductionmentioning

confidence: 99%

Modified MMS: Minimization Approach for Model Subset Selection

Rajathi,

Rukmani

2023

CMC

View full text Add to dashboard Cite

Considering the recent developments in the digital environment, ensuring a higher level of security for networking systems is imperative. Many security approaches are being constantly developed to protect against evolving threats. An ensemble model for the intrusion classification system yielded promising results based on the knowledge of many prior studies. This research work aimed to create a more diverse and effective ensemble model. To this end, selected six classification models, Logistic Regression (LR), Naive Bayes (NB), K-Nearest Neighbor (KNN), Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF) from existing study to run as independent models. Once the individual models were trained, a Correlation-Based Diversity Matrix (CDM) was created by determining their closeness. The models for the ensemble were chosen by the proposed Modified Minimization Approach for Model Subset Selection (Modified-MMS) from Lower triangular-CDM (L-CDM) as input. The proposed algorithm performance was assessed using the Network Security Laboratory-Knowledge Discovery in Databases (NSL-KDD) dataset, and several performance metrics, including accuracy, precision, recall, and F1-score. By selecting a diverse set of models, the proposed system enhances the performance of an ensemble by reducing overfitting and increasing prediction accuracy. The proposed work achieved an impressive accuracy of 99.26%, using only two classification models in an ensemble, which surpasses the performance of a larger ensemble that employs six classification models.

show abstract

A two-stage stacked ensemble intrusion detection system using five base classifiers and MLP with optimal feature selection

Cited by 17 publications

References 47 publications

Machine Learning Solutions for the Security of Wireless Sensor Networks: A Review

Machine Learning Solutions for the Security of Wireless Sensor Networks: A Review

Overcoming the Challenges of Data Lack, Leakage, and Dimensionality in Intrusion Detection Systems: A Comprehensive Review

Modified MMS: Minimization Approach for Model Subset Selection

Contact Info

Product

Resources

About