LAUSR

Rapid advancement in the sophistication of malware has posed a serious impact on the device connected over the Internet. Malware writing is driven by economic benefits; thus, an alarming increase in malware variants is witnessed. Recently, a large volume of malware attacks are reported on Internet of Things (IoT) networks; as these devices are exposed to insecure segments, further IoT devices reported have hardcoded credentials. To combat malware attacks on mobile devices and desktops, deep learning-based detection approaches have been attempted to detect malware variants. The existing solutions require large computational overhead and also have limited accuracy. In this paper, we visualize malware as Markov images to preserve semantic information of consecutive pixels. We further extract textures from Markov images using Gabor filter (named as Gabor images), and subsequently develop models using VGG-3 and Densely Connected Network (DenseNet). To encourage real-time malware detection and classification, we fine-tune Densely Connected Network. These models are trained and evaluated on two datasets namely Malimg and BIG2015. In our experimental evaluations, we found that DenseNet identifies Malimg and BIG2015 samples with accuracies of 99.94% and 98.98%, respectively. Additionally, the performance of our proposed method in classifying malware files to their respective families is superior compared to the state-of-the approach calibrated using prediction time, F1-score, and accuracy.