Özet:

Malware is software designed to damage computer-based systems, obtain or modify important information. This type of software targets network environments where people interact. Smart devices used in these network environments have become one of the indispensable parts of our lives today. Recently, many artificial intelligence-based studies have been carried out in order to ensure the security of smart devices and to detect malicious software. The dataset of this study consists of text-based content containing hidden malware types. The proposed approach consists of a preprocessing step and a deep learning model. In the preprocessing step, two new datasets were obtained by transforming the text-based data into 2-dimensional barcode types. In the next step, the feature sets were extracted by training the datasets by the designed deep network model. In the last step, the feature sets were combined and the classification process was carried out using the Softmax method. Experimental analyzes showed that the proposed approach increased the overall performance and the overall accuracy in the classification process was 100%.

Anahtar Kelimeler: