College of Education for Pure Sciences, University of Thi-Qar discussed a master dissertation on the early detection of bot attacks in the Internet of Things environment via using machine learning and deep learning by the postgraduate student, Mrs. Zainab Muhammad Ghadban.

The dissertation aimed at developing a suitable hybrid model to detect bot attacks in IoT devices and prevent the spread of malware.

The dissertation reviewed the implementation of machine learning techniques for binary classification that detects malware and normal traffic, and multiclass classification that detects nine malware and normal traffic.

The dissertation confirmed that most machine learning algorithms gave accurate results of more than 90%, and the best results were Adaboost via using only 18 features, as the algorithm got the best accuracy with 99.28 in binary classification and the RF algorithm with an accuracy of 86.51 using 17 features in multiple classification.