Malicious Network Traffic Detection Using Hybrid Feature Selection with Ensemble Neural Network

[{“box”:0,”content”:”n[if 992 equals=”Open Access”]n

n

n

n

Open Access

nn

n

n[/if 992]n[if 2704 equals=”Yes”]n

n

Notice

nThis is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.n

n[/if 2704]n

n

Year : 2025 [if 2224 equals=””]09/10/2025 at 10:55 AM[/if 2224] | [if 1553 equals=””] Volume : 27 [else] Volume : 27[/if 1553] | [if 424 equals=”Regular Issue”]Issue : [/if 424][if 424 equals=”Special Issue”]Special Issue[/if 424] [if 424 equals=”Conference”][/if 424] 03 | Page :

n

n

nn

n

n

n

    By

    n

    [foreach 286]n

    n

    Jermina F, Kanishka v, Rithika Shree A, Suman Adithya S R, Yogapriyan M,

    n t

  • n

    n[/foreach]

    n

n[if 2099 not_equal=”Yes”]n

    [foreach 286] [if 1175 not_equal=””]n t

  1. Asst. Professor, Student, Student, Student, Student, Department of CSE(cyber security) karpagam college of engineering, Coimbatore Tamilnadu, Department of CSE(cyber security) karpagam college of engineering, Coimbatore Tamilnadu, Department of CSE(cyber security) karpagam college of engineering, Coimbatore Tamil nadu, Department of CSE(cyber security) karpagam college of engineering, Coimbatore Tamil nadu, Department of CSE(cyber security) karpagam college of engineering, Coimbatore Tamil nadu, Tamil Nadu, Tamil Nadu, Tamil Nadu, Tamil Nadu, Tamil Nadu, india, India, India, India, India

    2. n[/if 1175][/foreach]

n[/if 2099][if 2099 equals=”Yes”][/if 2099]n

n

Abstract

n

n

nThe detection of malicious network traffic is a critical aspect of cybersecurity, aiming to protect sensitive data and maintain the integrity of network systems. This study introduces a novel approach that combines hybrid feature selection with ensemble neural networks to enhance the accuracy and efficiency of malicious network traffic detection. The dataset used in this study was obtained from Kaggle and offers a wide-ranging and varied collection of network traffic data. To select the most relevant features, a hybrid method combining Extra Trees Classifier (ETC) and Random Forest (RF) algorithms was employed. This approach helps identify the most important features, effectively lowering dimensionality and enhancing the overall performance of the model. After selecting the features, network traffic classification is carried out using a combination of neural network models, such as Convolutional Neural Networks (CNN), DenseNet, and an advanced version known as Enhanced Deep Convolutional Neural Network (EDCNN). By combining the strengths of different neural network architectures, the ensemble method creates a more reliable and effective classification model. CNNs are adept at capturing spatial hierarchies in data, DenseNet enhances feature propagation and reduces the vanishing gradient problem, while EDCNN combines the advantages of CNN with additional layers to improve detection capabilities. The experimental results clearly demonstrate that the proposed approach—combining hybrid feature selection with an ensemble neural network—leads to a significant improvement in the accuracy of detecting malicious network traffic when compared to conventional or traditional detection methods. The model consistently outperforms baseline techniques by effectively identifying subtle and complex patterns within the data that are often overlooked by simpler algorithms. This notable enhancement in detection capabilities can be attributed to the synergy between intelligent feature selection, which filters out irrelevant or redundant information, and the robustness of ensemble learning, which leverages the strengths of multiple neural network models to make more reliable predictions. This research makes a valuable contribution to the ongoing efforts in strengthening cybersecurity frameworks. It provides evidence that incorporating advanced machine learning strategies, especially those that utilize both feature optimization and model aggregation, can lead to more proactive and precise threat detection systems. The findings underscore the potential of such approaches in real-world applications, where the rapid identification of threats is crucial for protecting sensitive data and maintaining the integrity of network operations. As cyber threats continue to evolve in sophistication, this work highlights the importance of adopting innovative, data-driven solutions to stay ahead of potential attackers.nn

n

n

n

Keywords: Extra Trees Classifier (ETC), Enhanced Deep Convolutional Neural Network (EDCNN), Random Forest (RF),Malicious Network Traffic Detection ,Hybrid Feature Selection

n[if 424 equals=”Regular Issue”][This article belongs to Nano Trends – A Journal of Nano Technology & Its Applications ]

n

[/if 424][if 424 equals=”Special Issue”][This article belongs to Special Issue under section in Nano Trends – A Journal of Nano Technology & Its Applications (nts)][/if 424][if 424 equals=”Conference”]This article belongs to Conference [/if 424]

n

n

n

How to cite this article:
nJermina F, Kanishka v, Rithika Shree A, Suman Adithya S R, Yogapriyan M. [if 2584 equals=”][226 wpautop=0 striphtml=1][else]Malicious Network Traffic Detection Using Hybrid Feature Selection with Ensemble Neural Network[/if 2584]. Nano Trends – A Journal of Nano Technology & Its Applications. 09/10/2025; 27(03):-.

n

How to cite this URL:
nJermina F, Kanishka v, Rithika Shree A, Suman Adithya S R, Yogapriyan M. [if 2584 equals=”][226 striphtml=1][else]Malicious Network Traffic Detection Using Hybrid Feature Selection with Ensemble Neural Network[/if 2584]. Nano Trends – A Journal of Nano Technology & Its Applications. 09/10/2025; 27(03):-. Available from: https://journals.stmjournals.com/nts/article=09/10/2025/view=0

nn

n

n[if 992 equals=”Open Access”]Full Text PDF[/if 992]n

n

n[if 992 not_equal=”Open Access”]n

n

n[/if 992]n

nn

nnn

n[if 379 not_equal=””]nn

Browse Figures

n

n

n[foreach 379]

figures

[/foreach]n

n

n

n[/if 379]

n

n

n

n

n

References n

n[if 1104 equals=””]n

1. Sharma A, Gupta S, Singh P. Malicious network traffic detection using hybrid feature selection with ensemble neural networks. J Cybersecurity Netw Intell. 2023;15(4):123-45.
2. Zhao M, Wang H, Liu L. A hybrid feature selection approach for network intrusion detection using genetic algorithms and deep learning. IEEE Trans Inf Forensics Secur. 2022;17(2):324-37.
3. Kaur R, Singh J, Gupta MK. Ensemble neural networks for anomaly detection in high-dimensional network traffic. Int J Comput Netw Commun (IJCNC). 2021;14(6):90-105.
4. Kumar S, Jain V, Patel A. Real-time network threat detection using hybrid feature selection and ensemble deep learning models. J Netw Comput Appl. 2022;99(1):110-20.
5. Li D, Zhang X, Chen Y. Advanced intrusion detection systems using hybrid feature engineering and neural network ensembles. Proc IEEE Conf Cybersecurity Privacy. 2023:345-53.
6. Nguyen T, Mahdavinejad M, Ghanbari A. Hybrid machine learning model for network traffic anomaly detection using feature selection and ensemble methods. IEEE Access. 2022;10:76215-30.
7. Zhao X, Wu Y, Li R. A novel hybrid feature selection method using ReliefF and random forest for detecting network intrusions. J Appl Secur Res. 2022;17(3):204-21.
8. Wang J, He K, Zhang P. Efficient anomaly detection in network traffic through hybrid feature selection and ensemble deep neural networks. ACM Trans Internet Technol (TOIT). 2023;21(4):1-19.
9. Tang L, Feng Y, Zhou S. Ensemble learning-based model for robust network traffic anomaly detection with hybrid feature engineering. J Netw Comput Appl. 2021;154:102497.
10. Wang P, Xu H, Li F. Cybersecurity threat detection using deep ensemble learning with hybrid feature selection. Comput Secur. 2023;121:102789.
11. Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach Learn. 2006;63:3-42.
12. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017;60(6):84-90.
13. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR). 2017:4700-8

nn[/if 1104][if 1104 not_equal=””]n

    [foreach 1102]n t

  1. [if 1106 equals=””], [/if 1106][if 1106 not_equal=””],[/if 1106]

    2. n[/foreach]

n[/if 1104]

n

nn[if 1114 equals=”Yes”]n

n[/if 1114]

n

n

[if 424 not_equal=””]Regular Issue[else]Published[/if 424] Subscription Review Article

n

n

[if 2146 equals=”Yes”][/if 2146][if 2146 not_equal=”Yes”][/if 2146]n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n[if 1748 not_equal=””]

[else]

[/if 1748]n

n[if 1746 equals=”Retracted”]n

n

n

n

[/if 1746]n[if 4734 not_equal=””]

n

n

n

[/if 4734]n

n

Volume 27
[if 424 equals=”Regular Issue”]Issue[/if 424][if 424 equals=”Special Issue”]Special Issue[/if 424] [if 424 equals=”Conference”][/if 424] 03
Received 25/03/2025
Accepted 14/04/2025
Published 09/10/2025
Retracted
Publication Time 198 Days

n

n

89

nn

n

Login

n
My IP
n

PlumX Metrics

nn

n

n

n[if 1746 equals=”Retracted”]n

[/if 1746]nnn

nnn”}]