Design and Implementation of Secured Deep Learning Model for Prediction of Cyber Attacks in Computer Networks

M. Dharani, P. Murugesan, B. Vinothkumar, Kiruthika B., Kavya R., Sharmila Devi M.

2025

Abstract

This research develops a CNN-based deep learning model to predict cyberattacks in computer networks and compares it with an LSTM model. Materials and Methods: It considered two groups: (LSTM) and (CNN) of 26 samples each with a G Power of 80%, a threshold of 0.05, and a 95% confidence interval. Result: The CNN model outperformed the LSTM model in accuracy, 92.56% to 96.74%, while the LSTM model ranged between 85.42% to 91.87%. In addition, CNN had lower false positive rates ranging from 2.87% to 4.14% compared to LSTM, which had 4.32% to 6.89%. CNN also had a better stability, with a standard deviation of 1.6743, whereas LSTM had 2.8567. These results confirm the effectiveness of CNN in cyberattack detection, consistent with studies on cybersecurity and AI-based threat detection.

Paper Citation

in Harvard Style

Dharani M., Murugesan P., Vinothkumar B., B. K., R. K. and M. S. (2025). Design and Implementation of Secured Deep Learning Model for Prediction of Cyber Attacks in Computer Networks. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 789-795. DOI: 10.5220/0013920800004919

in Bibtex Style

@conference{icrdicct`2525,
author={M. Dharani and P. Murugesan and B. Vinothkumar and Kiruthika B. and Kavya R. and Sharmila M.},
title={Design and Implementation of Secured Deep Learning Model for Prediction of Cyber Attacks in Computer Networks},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={789-795},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013920800004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Design and Implementation of Secured Deep Learning Model for Prediction of Cyber Attacks in Computer Networks
SN - 978-989-758-777-1
AU - Dharani M.
AU - Murugesan P.
AU - Vinothkumar B.
AU - B. K.
AU - R. K.
AU - M. S.
PY - 2025
SP - 789
EP - 795
DO - 10.5220/0013920800004919
PB - SciTePress