•  
  •  
 

Document Type

Article

Keywords

Cybersecurity, Malware detection, Internet of Things (IoT), Machine Learning (ML), Deep Learning (DL), Federated Learning (FL)

Abstract

The rapid proliferation of Internet of Things (IoT) devices has significantly increased the threat landscape, with malwares arising as a critical concern. Advanced learning methods such as machine learning (ML), deep learning (DL), and federated learning (FL) are essential for handling complex IoT data. ML provides tools for pattern identification and detecting anomalies. DL boosts malware detection by automatically extracting features and identifying patterns. FL enables collaborative model training across decentralized devices, ensuring data privacy, which is crucial for diverse IoT systems. This comprehensive review specifically synthesizes ML, DL and FL for malware detection in the IoT environment, highlighting key trends and developments. Additionally, several significant contributions have been provided, including an overview of various types of malwares and their approaches and a comparison with existing studies. Importantly, notable trends and advancements are highlighted, and the current limitations of these learning techniques in malware detection are identified. It concludes by outlining future research directions to develop robust, scalable malware detection mechanisms tailored to safeguard the prosperity of the IoT environment against evolving cyber threats.

Download

Share

COinS