A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Filters
Towards Effective Network Intrusion Detection: From Concept to Creation on Azure Cloud
2021
IEEE Access
In the proposed study, we have presented a meta-classification approach using decision jungle to perform both binary and multiclass classification. ...
We have established the robustness of our approach by configuring an optimal set of hyper-parameters coupled with relevant feature subsets using a production-ready environment namely Azure machine learning ...
Additionally, misuse (signature-based) and anomaly-based are the other two types of IDS based on detection mechanisms. ...
doi:10.1109/access.2021.3054688
fatcat:bp3g5iqds5fuxokzwup2o5cvmm
An Anomaly Mitigation Framework for IoT Using Fog Computing
2020
Electronics
The anomaly-based module using the XGBoost classifier detects attacks with an accuracy of 99% and at least 97% for average recall, average precision, and average F1 score for binary and multiclass classification ...
We evaluated the performance of both modules using an IoT-based dataset in terms response time for the signature-based module and accuracy in binary and multiclass classification for the anomaly-based ...
Probe iii.R2L NSL KDD An Ensemble Learning 9 based Network Intrusion Detection System (ELNIDS) Anomaly-based Ensemble ML Experiments Routing attacks. ...
doi:10.3390/electronics9101565
fatcat:jzvsxl3wkffvrif6lickyrzvcm
Improving the Performance of Machine Learning-Based Network Intrusion Detection Systems on the UNSW-NB15 Dataset
2021
Computational Intelligence and Neuroscience
Our proposed system is a dynamically scalable multiclass machine learning-based network IDS. It consists of several stages based on supervised machine learning. ...
The new directions of the IDSs aim to leverage the machine learning models to design more robust systems with higher detection rates and lower false alarm rates. ...
Acknowledgments e authors thank the Department of Telecommunications at the Higher Institute for Applied Sciences and Technology for full support. ...
doi:10.1155/2021/5557577
fatcat:s3z2jh4z6jh6ld56jtwhxx6ga4
Authors Index
2021
2021 Tenth International Conference on Intelligent Computing and Information Systems (ICICIS)
Hala Abdel-Galil Ensemble Model-based Weighted Categorical Cross-entropy Loss for Facial Expression Recognition Hala M. ...
Ghaleb Content-based Image Retrieval based on Convolutional Neural Networks Mostafa Alaa A Survey on Learning-Based Intrusion Detection Systems for IoT Networks Mostafa Essa Anomaly Detection using Unsupervised ...
Radwa Reda Attention Detection using Electro-oculography ...
doi:10.1109/icicis52592.2021.9694196
fatcat:bx3n453xyrafjbbbelaxqhmbfm
GTF: An Adaptive Network Anomaly Detection Method at the Network Edge
2021
Security and Communication Networks
In this paper, we propose an adaptive ensemble-based method, named GTF, which combines TabTransformer and GBDT to leverage categorical and numerical features effectively and introduces Focal Loss to mitigate ...
Network Anomaly Detection (NAD) has become the foundation for network management and security due to the rapid development and adoption of edge computing technologies. ...
As a result, network security is a critical concern in our daily lives and business operations. ere is an urgent need for efficient and reliable anomaly detection mechanisms to shield our network. ...
doi:10.1155/2021/3017797
fatcat:lkswlqk4pnfkfo6imo32eub33a
Design and Development of RNN Anomaly Detection Model for IoT Networks
2022
IEEE Access
First, this paper proposes a novel deep learning model for anomaly detection in IoT networks using a recurrent neural network. ...
Finally, a lightweight deep learning model for binary classification was proposed using LSTM, BiLSTM, and GRU based approaches. ...
[79] used machine learning approaches to design and evaluate an anomaly based IoT NIDS. ...
doi:10.1109/access.2022.3176317
fatcat:3haetnnq2nfjxgpphsc7rvxgti
An Optimal NIDS for VCN Using Feature Selection and Deep Learning Technique
2021
International Journal of Digital Crime and Forensics
The existing approaches that use the conventional neural network cannot utilize all information for identifying the intrusions. In this paper, the anomaly-based NIDS for VCN is proposed. ...
The protection of VCN is required to maintain the faith of the cloud users. Intrusion detection is essential to secure any network. ...
detection, where ML techniques, ensemble techniques, DL techniques, and shallow learning techniques are utilized. ...
doi:10.4018/ijdcf.20211101.oa10
fatcat:wsr5o3naivasjldacavcpcz3ua
A Review on IoT Intrusion Detection Systems Using Supervised Machine Learning: Techniques, Datasets, and Algorithms
2023
UHD Journal of Science and Technology
Then, based on evaluating and contrasting recent studies in the field of IoT intrusion detection, a review regarding the IoT IDSs is offered with regard to the methodologies, datasets and machine learning ...
Even though the IoT network is protected by encryption and authentication, cyber-attacks are still possible. Consequently, it's crucial to have an intrusion detection system (IDS) technology. ...
An intelligent anomaly detection system called Anomaly Detection IoT (AD-IoT) which used the UNSW-NB15 dataset and RF to identify binary labeled categorization had been proposed. ...
doi:10.21928/uhdjst.v7n1y2023.pp53-65
fatcat:bhhrunxsgvhi7eco74alv2oi2u
Comparison and analysis of supervised machine learning algorithms
2021
Periodicals of Engineering and Natural Sciences (PEN)
In terms of detection rate, accuracy, false alarm rate, and Matthews correlation coefficient, supervised machine learning techniques surpass other algorithms. ...
Based on distance measurements, this study proposes algorithms for supervised machine learning. ...
A vector-based machine learning approach, SVM is generally a supervised model [18] . Two classes and two people are shown to be making use of categorization learning methods in Figure 1 . ...
doi:10.21533/pen.v9i4.2507
fatcat:sxr7lbwa3nfejgfsd75fgi7xxa
Using Machine Learning to Detect Cyber Attacks
2024
International Journal of Research Publication and Reviews
The study delves into the intricacies of feature selection, data preprocessing, and model evaluation techniques, pivotal components in refining the accuracy and efficiency of ML-based cybersecurity systems ...
This paper provides an in-depth exploration of the application of ML techniques in the realm of cyber attack detection. ...
In this paper [2] , a transfer learning and ensemble learning-based IDS is proposed for IoV systems using convolutional neural networks (CNNs) and hyper-parameter optimization techniques. ...
doi:10.55248/gengpi.5.0224.0555
fatcat:ck5trqwxwzbqfmvesekr7hjhcq
Ensemble Models for Intrusion Detection System Classification
2022
International Journal of Smart Sensor and Adhoc Network.
In this scope, we evaluated the usage of state-of-the-art ensemble learning models in improving the performance and efficiency of IDS/IPS. ...
of detection and high efficiency. ...
In the SDN environment, anomalies can be detected. This paper has discussed and applied a deep learning idea for detecting anomalies based on the flow. ...
doi:10.47893/ijssan.2022.1209
fatcat:m5hflzegz5es3kbscv4lpu5khq
Table of Contents
2021
2021 Tenth International Conference on Intelligent Computing and Information Systems (ICICIS)
..................... 154 Predicting the Big Five for social network users using their personality characteristics 160 Ensemble Model-based Weighted Categorical Cross-entropy Loss for Facial Expression ...
Using BERT Transformers .............. 207 Attention Detection using Electro-oculography Signals in E-learning Environment .... 213 Technologies, tools, and resources -driving forces in construction sector ...
doi:10.1109/icicis52592.2021.9694157
fatcat:qnwadgegdfbbrds3tvrz4wpr4q
An Approach for the Application of a Dynamic Multi-Class Classifier for Network Intrusion Detection Systems
2020
Electronics
Most of the studies use a unique machine learning model, identifying anomalies related to possible attacks. In other cases, machine learning algorithms are used to identify certain type of attacks. ...
Currently, the use of machine learning models for developing intrusion detection systems is a technology trend which improvement has been proven. ...
We used the method based on an ensemble model based on XGBoost to improve the detection rate. ...
doi:10.3390/electronics9111759
fatcat:mpw4ckwaurc2vi2kwoikrocgxq
Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools
[article]
2019
arXiv
pre-print
There has been considerable growth and interest in industrial applications of machine learning (ML) in recent years. ...
Automated machine learning (AutoML) has emerged as a way to save time and effort on repetitive tasks in ML pipelines, such as data pre-processing, feature engineering, model selection, hyperparameter optimization ...
H2O-Automl uses the combination of random grid search with stacked ensembles, as diversified models improve the accuracy of ensemble method. ...
arXiv:1908.05557v2
fatcat:vjvoor6gufemralwjqrhxzkuya
The Use of Ensemble Models for Multiple Class and Binary Class Classification for Improving Intrusion Detection Systems
2020
Sensors
Machine Learning Ensemble Models with base classifiers (J48, Random Forest, and Reptree) were built. ...
Binary classification, as well as Multiclass classification for KDD99 and NSLKDD datasets, was done while all the attacks were named as an anomaly and normal traffic. ...
Another multiclass classification that uses a heterogeneous ensemble model and outlier detection in a combination of numerous approaches and ensemble methods was developed by [3] . ...
doi:10.3390/s20092559
pmid:32365937
fatcat:mogkts24tfajbkdxvmtbzf4bta
« Previous
Showing results 1 — 15 out of 420 results