رسول شهسواري

Global Positioning System (GPS) spoofing is known as one of the serious challenges in navigation and global positioning systems, which can lead to security threats and malfunction of related devices. The purpose of this research is to design and eva‎luate machine learning algorithms to detect and deal with GPS spoofing attacks. In this research, seven different algorithms, including nearest neighbor, logistic regression, Gaussian naive Bayes, decision tree, random forest, support vector machine and enhanced gradient were used to detect GPS deception. For this purpose, a valid dataset including deception samples and Valid GPS signals were used. Each of the algorithms were eva‎luated based on the criteria of accuracy, speed and the ability to separate the deception signals from the valid signals. The results showed that the gradient enhanced algorithm achieved the best performance with an accuracy of 98.32% and was more effective in detecting deception than other algorithms. This research shows that machine learning algorithms can be effectively used in detecting and preventing GPS deception

فريب GPS , الگوريتم‌هاي يادگيري ماشين , دقت مدل

GPS deception , machine learning algorithms , model accuracy

RASOUL SHAHSAVARI

Dr.MAHDI NASIRI SARVI