Enhanced Deep Learning-Based Malware Classification Using MobileNetV2

In the rapidly evolving landscape of cybersecurity, the classification of malware has become increasingly critical due to the exponential growth in the volume of malware, which poses significant security threats to financial institutions, businesses, and individuals. Traditional signature-based detection methods have struggled to keep up with the growing variety and complexity of new threats, making it necessary to use more advanced techniques. Among these, deep learning has emerged as a promising approach for malware detection, particularly through the classification of malware images by transforming binary files into grayscale representations. While previous research has predominantly utilized deep learning architectures for this task. However, in this research work, we developed a model with Mobilenet to enhance classification accuracy. The results of this research demonstrate the revolutionary potential of deep learning-based methods for malware family classification.