Malware Classification Using Ghost Strategy Northern Goshawk Optimization with a Spatial Temporal Graph Convolutional Neural Network Based on Image Patterns

The rapid growth of malware variants has made malware classification an essential task for ensuring security.Different malware families require tailored techniques to effectively manage unique variants within each family.The existing methods often struggle with high dimensionality of malware images, which negatively impacts classification accuracy.This research proposes Ghost Strategy Northern Goshawk Optimization with Spatial Temporal Graph Convolutional Neural Network (GSNGO-STGCNN) technique for malware classification, which addresses dimensionality issues and significantly improves classification performance.Initially, data is acquired from the BIG15 and Malimg dataset, and pre-processing is carried out to convert binary data into grayscale images, facilitating the visualization of malware patterns.Feature extraction is performed using MobileNetV1, which involves depth-wise separable convolutions to efficiently capture image patterns.The GSNGO-STGCNN technique used for classification involves hyperparameter tuning to optimize the model's parameters, effectively detect malware patterns, and improve classification accuracy.The proposed method achieves a commendable accuracy of 99.12% on BIG15 dataset, and 99.25% on the Malimg dataset, thereby outperforming existing methods namely, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) techniques.