A Survey on Federated Learning for IoT Malware Analysis

The growth of the Internet of Things (IoT) is expanding rapidly. The count of devices being connected to the internet is growing profusely. IoT malware is malicious software that leads to data breaches, and disruption of the device's functionality and even the device. So, the detection of IoT malware is very crucial. Traditionally, centralized approaches are used for IoT malware analysis which can lead to privacy concerns. Among various approaches for IoT malware analysis, the one focused in this paper is Federated Learning (FL). FL is a collaborative approach in which model training takes place on individual devices, the data remains local to the end devices. FL provides many other advantages like data privacy, improved performance, and scalability. We have explored FL as a promising approach to secure IoT systems. We have discussed different FL techniques, their significance in enhancing IoT security, the challenges they face, and potential solutions.