Now the Industrial Internet of Things (IIoT) devices can be deployed to monitor the flow of data, the source of collection and supervision on a large scale of complex networks. It implements large networks for sending and receiving data connected by smart devices. Malware threats, which are primarily targeted at conventional computers linked to the Internet, can also be targeted at IoT machines. Therefore, a smart protection approach is needed to protect millions of IIoT users against malicious attacks. On the other hand, existing state-of - the-art malware identification methods are not better in terms of computational complexity. In this paper, we design architecture to detect malware attacks on the Industrial Internet of Things (MD-IIOT). For an in-depth analysis of malware, a methodology is proposed based on color image visualization and deep convolution neural network. The findings of the proposed method are compared to former approaches to malware detection. The experimental results indicate that the proposed method's predictive time and detection accuracy are higher than that of previous machine learning and deep learning methods.

现在，可以部署工业物联网（IIoT）设备来监视数据流，大规模复杂网络上的收集和监视源。它实现了大型网络，用于发送和接收由智能设备连接的数据。恶意软件威胁主要针对与Internet链接的常规计算机，也可以针对IoT计算机。因此，需要一种智能保护方法来保护数百万的IIoT用户免受恶意攻击。另一方面，就计算复杂性而言，现有的最新恶意软件识别方法并不更好。在本文中，我们设计了可检测工业物联网（MD-IIOT）上的恶意软件攻击的体系结构。为了深入分析恶意软件，提出了一种基于彩色图像可视化和深度卷积神经网络的方法。将该方法的发现与以前的恶意软件检测方法进行了比较。实验结果表明，该方法的预测时间和检测精度均高于以往的机器学习和深度学习方法。