Differential Privacy for Malware Detection in IoT Devices

Internet of Things (IoT) devices have become increasingly popular in recent years. This popularity is driven by their ability to improve human lives. As IoT technology continues to evolve and improve, malware is one of the main challenges in IoT devices where data-based methods like machine learning techniqes are widely used for detecting them. However, manufacturers and consumers of IoT devices are facing important challenges regarding privacy in collecting data.

The aim of this project, is to develop a framework for malware detection in IoT device systems that protects user data privacy at the same time. In this regards, some differential privacy based techniques will use in combination with deep learning methods. Differential privacy is a technique used to protect the privacy of individuals when analyzing their data. It involves adding random noise to the data before analyzing it in a way that ensures that the privacy of individuals is preserved. In the context of IoT malware detection, differential privacy can be used to protect the privacy of individuals whose devices are being monitored for malware.