Analyzing Network Traffic Features for IoT Malware Detection through Forensic Methods

This emerges as an issue given that the rapid proliferation of IoT (Internet of Things) devices came alongside several security issues in which IoT malware became an issue of interest in this regard. Due to the fact that IoT devices are of different kinds then their network interaction is also not uniform hence this work proposes a new approach for detecting IoT malware using forensic methods that analyze network traffic features. The focus of the study will be on the network traffic patterns (data flow, packet characteristics and communication protocols) in order to identify anomalous behaviors which are likely to contain malicious activity. Forensic analysis techniques are applied on network logs to build up a picture of what attack scenarios might look like and where suspicious traffic is coming from. Statistical and machine learning methods are applied at an advanced level to classify traffic as normal or abnormal in order to improve detection accuracy. This approach provides a non-intrusive and scalable solution for real-time detection of IoT malware without exposing vulnerable IoT ecosystems to emerging threats.