A Cyber-Attack Detection System Using Late Fusion Aggregation Enabled Cyber-Net

Today, securing devices connected to the internet is challenging as security threats are generated through various sources. The protection of cyber-physical systems from external attacks a primary task. presented method planned on prime motive detecting cybersecurity and their impacted parameters. proposed architecture employs LYSIS dataset formulates Multi Variant Exploratory Data Analysis (MEDA) Principle Component (PCA) Singular Value Decomposition (SVD) for extraction unique feature mappings analyzed with Recurrent 2 Convolutional Neural Network (R2CNN) Gradient Boost Regression (GBR) identify maximum correlation. Novel Late Fusion Aggregation enabled Cyber-Net (LFAEC) robust derived algorithm. quantitative analysis uses predicted threat points actual variables which mean difference vectors evaluated. performance system assessed against parameters such Accuracy, Precision, Recall, F1 Score. outperformed by 98% 100% in all quality measures compared existing methods.