International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 66 |
Published: February 2025 |
Authors: Chaitali V. Chaudhary, S. Vanitha |
![]() |
Chaitali V. Chaudhary, S. Vanitha . An Enhanced Anomaly Detection in Networked Systems through Deep Learning Model. International Journal of Computer Applications. 186, 66 (February 2025), 1-6. DOI=10.5120/ijca2025924451
@article{ 10.5120/ijca2025924451, author = { Chaitali V. Chaudhary,S. Vanitha }, title = { An Enhanced Anomaly Detection in Networked Systems through Deep Learning Model }, journal = { International Journal of Computer Applications }, year = { 2025 }, volume = { 186 }, number = { 66 }, pages = { 1-6 }, doi = { 10.5120/ijca2025924451 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2025 %A Chaitali V. Chaudhary %A S. Vanitha %T An Enhanced Anomaly Detection in Networked Systems through Deep Learning Model%T %J International Journal of Computer Applications %V 186 %N 66 %P 1-6 %R 10.5120/ijca2025924451 %I Foundation of Computer Science (FCS), NY, USA
In the rapidly evolving digital landscape, the proliferation of interconnected devices and networks has introduced unprecedented security challenges. As cyber threats evolve in complexity there is a pressing need for robust intrusion detection systems (IDS) capable of safeguarding against a wide range of attacks. This paper explores the efficacy of utilizing deep learning techniques, specifically a multi-scale convolutional neural network (M-CNN) for detecting network intrusions using the CSE-CIC-IDS2018[9] dataset. The study focuses on meticulous data preprocessing techniques to enhance model performance and presents a streamlined approach for intrusion detection. Through comprehensive experimentation and evaluation, the proposed M-CNN model demonstrates high accuracy, precision, recall, and F1-score for detecting various types of network intrusions comapred to other studies, highlighting its effectiveness in mitigating cyber threats in modern networks.