International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 66 |
Published: February 2025 |
Authors: Md. Anisur Rahman, Md. Sahidullah, Farjana Kamal Konok |
![]() |
Md. Anisur Rahman, Md. Sahidullah, Farjana Kamal Konok . Real-time Threat Analysis and Improving Cybersecurity Defenses in Evolving Environments with Deep Learning and Traditional Machine Learning Algorithms. International Journal of Computer Applications. 186, 66 (February 2025), 31-39. DOI=10.5120/ijca2025924444
@article{ 10.5120/ijca2025924444, author = { Md. Anisur Rahman,Md. Sahidullah,Farjana Kamal Konok }, title = { Real-time Threat Analysis and Improving Cybersecurity Defenses in Evolving Environments with Deep Learning and Traditional Machine Learning Algorithms }, journal = { International Journal of Computer Applications }, year = { 2025 }, volume = { 186 }, number = { 66 }, pages = { 31-39 }, doi = { 10.5120/ijca2025924444 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2025 %A Md. Anisur Rahman %A Md. Sahidullah %A Farjana Kamal Konok %T Real-time Threat Analysis and Improving Cybersecurity Defenses in Evolving Environments with Deep Learning and Traditional Machine Learning Algorithms%T %J International Journal of Computer Applications %V 186 %N 66 %P 31-39 %R 10.5120/ijca2025924444 %I Foundation of Computer Science (FCS), NY, USA
Real-time threat analysis plays a critical role in modern cybersecurity, ensuring that systems remain protected against evolving cyber threats. This study aims to develop and evaluate a robust model for threat detection using a combination of deep learning and traditional machine learning algorithms. The proposed methodology employs deep learning techniques alongside traditional algorithms, leveraging a comprehensive threat detection dataset for training and validation. The model achieved the highest accuracy of 97% with minimal loss, converging efficiently within the initial training epochs. Results indicate that the model achieved reliable generalization with close alignment between training and validation performance, showcasing its effectiveness in detecting threats accurately. The contributions of this study lie in advancing cybersecurity mechanisms through the integration of machine learning models, paving the way for enhanced real-time threat detection and response. Future enhancements, including advanced architectures such as Transformers, are proposed to further improve performance and applicability across broader cybersecurity domains.