Anomaly-based network intrusion detection with ensemble classifiers and meta-heuristic scale (ECMHS) in traffic flow streams

Dasari, Durga Bhavani; Edamadaka, Gayathri; Ch, Smitha Chowdary; Sobhana, M.

doi:10.1007/s12652-020-02628-1

Cited by 11 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their application of autoencoders with the Modbus TCP protocol yielded an impressive F1 score of 98.36%. Similarly, [11][12][13] introduced an unsupervised Attention-based ConvLSTM Autoencoder with a Dynamic Thresholding (ACLAE-DT) framework for handling multivariate time series anomalies. By processing the data and creating feature images, they utilized an attention-based ConvLSTM autoencoder to discern temporal behaviors, achieving AD through dynamic thresholding of reconstruction errors [14][15].…”

Section: Literature Reviewmentioning

confidence: 99%

Adaptive Approach to Anomaly Detection in Internet of Things Using Autoencoders and Dynamic Thresholds

Shanmugam

et al. 2024

JMC

View full text Add to dashboard Cite

The Internet of Things (IoT) represents a vast network of interconnected devices, from simple sensors to intricate machines, which collect and share data across sectors like healthcare, agriculture, and home automation. This interconnectivity has brought convenience and efficiency but also introduced significant security concerns. Many IoT devices, built for specific functions, may lack robust security, making them vulnerable to cyberattacks, especially during device-to-device communications. Traditional security approaches often fall short in the vast and varied IoT landscape, underscoring the need for advanced Anomaly Detection (AD), which identifies unusual data patterns to warn against potential threats. Recently, a range of methods, from statistical to Deep Learning (DL), have been employed for AD. However, they face challenges in the unique IoT environment due to the massive volume of data, its evolving nature, and the limitations of some IoT devices. Addressing these challenges, the proposed research recommends using autoencoders with a dynamic threshold mechanism. This adaptive method continuously recalibrates, ensuring relevant and precise AD. Through extensive testing and comparisons, the study seeks to demonstrate the efficiency and adaptability of this approach in ensuring secure IoT communications.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Adaptive Approach to Anomaly Detection in Internet of Things Using Autoencoders and Dynamic Thresholds

Shanmugam

et al. 2024

JMC

View full text Add to dashboard Cite

show abstract

“…The HC idea was to incorporate the MFO technique for enhancing the convergence rates. In [20], an MH association scale can be devised for extracting threshold values for the transaction and ensemble classifications can be employed for analyzing the transaction as attack or normal. In the presented mechanism Ensemble classifier was utilized depending on drift identification having the capability for examining the requests at stream levels.…”

Section: Related Workmentioning

confidence: 99%

Barnacles Mating Optimizer with Hopfield Neural Network Based Intrusion Detection in Internet of Things Environment

2023

Teh. vjesn.

View full text Add to dashboard Cite

Owing to the development and expansion of energy-aware sensing devices and autonomous and intelligent systems, the Internet of Things (IoT) has gained remarkable growth and found uses in several day-to-day applications. Currently, the Internet of Things (IoT) network is gradually developing ubiquitous connectivity amongst distinct new applications namely smart homes, smart grids, smart cities, and several others. The developing network of smart devices and objects allows people to make smart decisions with machine to machine (M2M) communications. One of the real-world security and IoT-related challenges was vulnerable to distinct attacks which poses several security and privacy challenges. Thus, an IoT provides effective and efficient solutions. An Intrusion Detection System (IDS) is a solution for addressing security and privacy challenges with identifying distinct IoT attacks. This study develops a new Barnacles Mating Optimizer with Hopfield Neural Network based Intrusion Detection (BMOHNN-ID) in IoT environment. The presented BMOHNN-ID technique majorly concentrates on the detection and classification of intrusions from IoT environments. In order to attain this, the BMOHNN-ID technique primarily pre-processes the input data for transforming it into a compatible format. Next, the HNN model was employed for the effectual recognition and classification of intrusions from IoT environments. Moreover, the BMO technique was exploited to optimally modify the parameters related to the HNN model. When a list of possible susceptibilities of every device is ordered, every device is profiled utilizing data related to every device. It comprises routing data, the reported hostname, network flow, and topology. This data was offered to the external modules for digesting the data via REST API model. The experimental values assured that the BMOHNN-ID model has gained effectual intrusion classification performance over the other models.

show abstract

“…The metaclusterer filtered clusterer algorithm permits to apply the filter before clusrerer is been learnt. The training data form the shape of the structure clusterer while the test data processed by using the filter without affecting the structure [67]. All these algorithms are implementing with the dataset with all features after applying SMOTE filter and observing the performance accuracy.…”

Section: Model Implementationmentioning

confidence: 99%

A prediction model based machine learning algorithms with feature selection approaches over imbalanced dataset

Hamoud

Kamel²,

Gaafar³

et al. 2022

IJEECS

View full text Add to dashboard Cite

The educational sector faced many types of research in predicting student performance based on supervised and unsupervised machine learning algorithms. Most students' performance data are imbalanced, where the final classes are not equally represented. Besides the size of the dataset, this problem affects the model's prediction accuracy. In this paper, the Synthetic Minority Oversampling Technique (SMOTE) filter is applied to the dataset to find its effect on the model's accuracy. Four feature selection approaches are applied to find the most correlated attributes that affect the students' performance. The SMOTE filter is examined before and after applying feature selection approaches to measure the model's accuracy with supervised and unsupervised algorithms. Three supervised/unsupervised algorithms are examined based on feature selection approaches to predict the students' performance. The findings show that supervised algorithms (LMT, Simple Logistic, and Random Forest) got high accuracy after applying SMOTE without feature selection. The prediction accuracies of unsupervised algorithms (Canopy, EM, and Farthest First) are enhanced after applying feature selection approaches and SMOTE filter.

show abstract

Anomaly-based network intrusion detection with ensemble classifiers and meta-heuristic scale (ECMHS) in traffic flow streams

Cited by 11 publications

References 29 publications

Adaptive Approach to Anomaly Detection in Internet of Things Using Autoencoders and Dynamic Thresholds

Adaptive Approach to Anomaly Detection in Internet of Things Using Autoencoders and Dynamic Thresholds

Barnacles Mating Optimizer with Hopfield Neural Network Based Intrusion Detection in Internet of Things Environment

A prediction model based machine learning algorithms with feature selection approaches over imbalanced dataset

Contact Info

Product

Resources

About