Due to its simple installation and connectivity, the Internet of Things (IoT) is susceptible to malware attacks. Being able to operate autonomously. As IoT devices have become more prevalent, they have become the most tempting targets for malware. Weak, guessable, or hard-coded passwords, and a lack of security measures contribute to these vulnerabilities along with insecure network connections and outdated update procedures. To understand IoT malware, current methods and analysis ,using static methods, are ineffective. The field of deep learning has made great strides in recent years due to their tremendous data mining, learning, and expression capabilities, cybersecurity has enjoyed tremendous growth in recent years. As a result, malware analysts will not have to spend as much time analyzing malware. In this paper, we propose a novel detection and analysis method that harnesses the power and simplicity of decision trees. The experiments are conducted using a real word dataset, MaleVis which is a publicly available dataset. Based on the results, we show that our proposed approach outperforms existing state-of-the-art solutions in that it achieves 97.23% precision and 95.89% recall in terms of detection and classification. A specificity of 96.58%, F1-score of 96.40%, an accuracy of 96.43.

翻译：由于其安装简便和互联性，物联网（IoT）容易遭受恶意软件攻击，且能够自主运行。随着物联网设备日益普及，它们已成为恶意软件最具诱惑力的攻击目标。弱密码、可猜测或硬编码密码，以及安全措施缺失，加上不安全的网络连接和陈旧的更新程序，共同导致了这些漏洞。在理解物联网恶意软件方面，现有方法和基于静态分析的手段效果不佳。近年来，深度学习凭借其强大的数据挖掘、学习和表达能力取得了巨大进展，网络安全领域也随之蓬勃发展。这使得恶意软件分析师无需花费大量时间进行分析。本文提出了一种新颖的检测与分析方法，利用决策树的强大功能与简洁性。实验使用真实世界数据集MaleVis（一个公开数据集）进行。结果表明，我们提出的方法优于现有最先进解决方案，在检测与分类方面实现了97.23%的精确率和95.89%的召回率，特异性为96.58%，F1分数为96.40%，准确率为96.43%。