International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 186 - Issue 30 |
Published: July 2024 |
Authors: Shreyas Anand |
![]() |
Shreyas Anand . Data Driven Approaches to Cybersecurity Using Deep Learning. International Journal of Computer Applications. 186, 30 (July 2024), 24-32. DOI=10.5120/ijca2024923844
@article{ 10.5120/ijca2024923844, author = { Shreyas Anand }, title = { Data Driven Approaches to Cybersecurity Using Deep Learning }, journal = { International Journal of Computer Applications }, year = { 2024 }, volume = { 186 }, number = { 30 }, pages = { 24-32 }, doi = { 10.5120/ijca2024923844 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2024 %A Shreyas Anand %T Data Driven Approaches to Cybersecurity Using Deep Learning%T %J International Journal of Computer Applications %V 186 %N 30 %P 24-32 %R 10.5120/ijca2024923844 %I Foundation of Computer Science (FCS), NY, USA
The increasing complexity of cyber threats necessitates innovative approaches for pre-emptive defense mechanisms. This research paper focuses on the application of deep learning techniques as a critical tool for monitoring and preventing cyber-attacks. In the realm of cybersecurity, machine learning, and deep learning classification algorithms play pivotal roles in identifying system irregularities indicative of ongoing attacks. Six classification techniques were employed in this study, including traditional machine learning algorithms (Decision Tree, Random Forest, and Gradient Boosting) and advanced deep learning algorithms (Convolutional Neural Network [CNN], Long Short-Term Memory [LSTM], and LSTM plus CNN). Using metrics such as precision, accuracy, F1-score, and recall, their performance was evaluated on the widely used Kaggle dataset CSIC 2010 Web Application Attacks. The findings of the study reveal that the LSTM with CNN exhibits superior performance, showcasing its effectiveness in detecting and defending against diverse cyber threats. This study underscores the urgency and practical benefits of integrating deep learning into cybersecurity protocols to safeguard networks from external and internal threats.