Malicious Code Variant Identification Based on Multiscale Feature Fusion CNNs.

The increasing volume and types of malwares bring a great threat to network security. The malware binary detection with deep convolutional neural networks (CNNs) has been proved to be an effective method. However, the existing malware classification methods based on CNNs are unsatisfactory to this day because of their poor extraction ability, insufficient accuracy of malware classification, and high cost of detection time. To solve these problems, a novel approach, namely, multiscale feature fusion convolutional neural networks (MFFCs), was proposed to achieve an effective classification of malware based on malware visualization utilizing deep learning, which can defend against malware variants and confusing malwares. The approach firstly converts malware code binaries into grayscale images, and then, these images will be normalized in size by utilizing the MFFC model to identify malware families. Comparative experiments were carried out to verify the performance of the proposed method. The results indicate that the MFFC stands out among the recent advanced methods with an accuracy of 98.72% and an average cost of 5.34 milliseconds on the Malimg dataset. Our method can effectively identify malware and detect variants of malware families, which has excellent feature extraction capability and higher accuracy with lower detection time.