Hybridizing Base-Line 2D-CNN Model with Cat Swarm Optimization for Enhanced Advanced Persistent Threat Detection

TL;DR

This research paper presents an innovative approach that leverages Convolutional Neural Networks with a 2D baseline model, enhanced by the cutting-edge Cat Swarm Optimization (CSO) algorithm, to significantly improve APT detection accuracy.

Abstract

In the realm of cyber-security, detecting Advanced Persistent Threats (APTs) remains a formidable challenge due to their stealthy and sophisticated nature. This research paper presents an innovative approach that leverages Convolutional Neural Networks (CNNs) with a 2D baseline model, enhanced by the cutting-edge Cat Swarm Optimization (CSO) algorithm, to significantly improve APT detection accuracy. By seamlessly integrating the 2D-CNN baseline model with CSO, we unlock the potential for unprecedented accuracy and efficiency in APT detection. The results unveil an impressive accuracy score of $98.4\%$, marking a significant enhancement in APT detection across various attack stages, illuminating a path forward in combating these relentless and sophisticated threats.

Figures (5)

• Figure 1: The proposed model framework of CSO-2D-CNN
• Figure 2: Convergence - Optimization Results Curves depicting the detection of attacks across various stages of an APT using the proposed CSO-2D-CNN model trained on the DAPT2020 dataset.
• Figure 3: Accuracy - Optimization Results of CSO-2D-CNN model. Additionally, the model returns the value of the best fitness.
• Figure 4: Confusion Matrix for CSO-2D-CNN Model
• Figure 5: Receiver Operating Characteristic (ROC) curve for CSO-2D-CNN model