Unmanned Aerial Vehicles (UAVs) require Global Navigation Satellite Systems (GNSS) for navigation and control. The UAVs are unable to follow the way-points of the intended path in jamming conditions without GNSS signals. However, the GNSS receiver is susceptible to many types of jammers, which degrades the quality of service. Jamming detection is crucial for increasing the location's accuracy as a result. The original signal's frequency is shared by the interfering signal. Therefore, traditional techniques have difficulty extracting the features. This paper proposes a Deep Learning (DL) model for signal jamming detection which uses Bidirectional Long-Short Term Memory (Bi-LSTM) to process data sequentially
in succeeding leads and classify it into normal and interfering signals. The confusion matrix summarizes the outcomes. The simulation findings demonstrate that the prediction capability and interference detection precision are better than unidirectional Long-Short Term Memory (LSTM).