We will use this Data set:
“Edge-IIoTset Cyber Security Dataset of IoT & IIoT”
In this dataset, The IoT data are generated from various IoT devices (more than 10 types) such as Low-cost digital sensors for sensing temperature and humidity, Ultrasonic sensor, Water level detection sensor, pH Sensor Meter, Soil Moisture sensor, Heart Rate Sensor, Flame Sensor, …etc.). However, we identify and analyze fourteen attacks related to IoT and IIoT connectivity protocols, which are categorized into five threats, including, DoS/DDoS attacks, Information gathering, Man in the middle attacks, Injection attacks, and Malware attacks. After processing and analyzing the proposed realistic cyber security dataset, we provide a primary exploratory data analysis and evaluate the performance our machine learning model.
We are using CNN model for detecting any type of Intrusion in IoT devices. The dataset encompasses a broad range of IoT and IIoT applications, making it ideal for training a CNN-based model to recognize patterns indicative of attacks. By transforming the sequential sensor data into a suitable format, CNNs can automatically learn features that distinguish normal behaviors from various attack types. The trained CNN can then be used to analyze incoming IoT data and identify deviations from expected patterns and detecting attacks. Through its ability to capture complex relationships within the data, the CNN acts as a powerful tool for enhancing the security of IoT systems by promptly detecting Attacks in IoT devices.