Scholarlink

The emergence of the IoT has initiated a period of interconnected devices, revolutionizing various industries. However, this rapid increase has also introduced significant security vulnerabilities, making IoT networks primary targets for malware attacks. This study highlights the uses of machine learning(ML) techniques to enhance malware detection in IoT networks. Employing traditional machine learning algorithms (e.g., Random Forest, Support Vector Machine, and K-Nearest Neighbour) alongside boosting algorithms, such as XGBoost, the study demonstrates the efficacy of these models in accurately identifying and classifying malware samples. The results underscore the potential of ML to fortify cybersecurity in IoT environments, showcasing its high accuracy and efficiency in malware detection. This research contributes to the growing body of study in IoT security by presenting a comprehensive methodology for malware detection that leverages advanced ML techniques.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Malware Detection in Internet of Things Using Machine Learning and Feature Extraction Techniques

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Anindita Sarkar,
  • Manas Barman,
  • Sheikh Marriah Rukhser,
  • Dharitri Brahma,
  • Bhagyasri Bora,
  • Amitava Nag

摘要

The emergence of the IoT has initiated a period of interconnected devices, revolutionizing various industries. However, this rapid increase has also introduced significant security vulnerabilities, making IoT networks primary targets for malware attacks. This study highlights the uses of machine learning(ML) techniques to enhance malware detection in IoT networks. Employing traditional machine learning algorithms (e.g., Random Forest, Support Vector Machine, and K-Nearest Neighbour) alongside boosting algorithms, such as XGBoost, the study demonstrates the efficacy of these models in accurately identifying and classifying malware samples. The results underscore the potential of ML to fortify cybersecurity in IoT environments, showcasing its high accuracy and efficiency in malware detection. This research contributes to the growing body of study in IoT security by presenting a comprehensive methodology for malware detection that leverages advanced ML techniques.