XAI-based RF Jamming Detection Framework for Vehicular Networks in Battlefield Environment

Modern military operations require communication among vehicles and drones are of utmost significance for mission success and troop safety. However, this communication is susceptible to Radio Frequency (RF) jamming attacks, which lead to channel disruption and compromise situational awareness. To address this challenge, this paper proposes an AI-based solution for predictive analysis of RF jamming attacks in Vehicular Adhoc Networks (VANETs). Our model utilizes an Artificial Neural Network (ANN) to classify attacks into three categories: No Attack, Reactive Jammer Attack, and Constant Jammer Attack, using features such as signal characteristics and channel information. Further, we employ Explainable AI (XAI) techniques, including SHAP and LIME, to enhance the interpretability and transparency of the model's predictions. Evaluation results demonstrate the effectiveness of our approach, achieving an accuracy of 93.00% on the test dataset. This research contributes to developing robust countermeasures against RF jamming in dynamic battlefield environments.