PerDet: Machine-Learning-Based UAV GPS Spoofing Detection Using Perception Data

To ensure that unmanned aerial vehicle (UAV) positioning is not affected by GPS spoofing signals, we propose PerDet, a perception-data-based UAV detection approach utilizing machine learning algorithms. Based on the principle of position estimation process and attitude process, choose data gathered accelerometer, gyroscope, magnetometer, barometer as features. Although these sensors have different shortcomings, their variety makes sure selected perception can compensate for each other. We collect experimental through real flights, which make PerDet more practical. Furthermore, run various algorithms our dataset select most effective classifier detector. Through performance evaluation comparison, demonstrate better than existing methods an method with detecting rate 99.69%. For fair reproduce it to compare between this approach.