Gradient Monitored Reinforcement Learning for Jamming Attack Detection in FANETs

Unmanned Aerial Vehicles (UAVs) have several military and civilian applications to perform tasks that do not require a central processing unit or human involvement. There are various vulnerable characteristics, alternatively limitations, in UAV systems such as data loss, signals interference, disabling sensors, misleading weapons, cyber attacks, disrupting services, etc. Jamming attack is one of the cyber threats that likely lead to denial of service that often occurs in wireless communication systems like Flying ad hoc networks (FANETs) and Internet of Drones (IoD). Over years, there are several approaches proposed by researchers to detect jamming attacks such as rule-based jamming attack detection mechanism, Bayesian game-theoretic mechanism, IoD-based protection mechanism, communication channel techniques (channel hopping, spectrum spreading, MIMO-based jamming mitigation, coding, etc), delay tolerant networking technique, and cryptographic algorithms, however, these methods were not suitable for jamming detection in UAV environment. The major challenges are on the delivery efficiency, processing time, accuracy, energy consumption, flight distance, and flight autonomy. In this paper, we introduce a method to detect the jamming attack using Reinforcement Learning-based Gradient Monitored (RLGM) mechanism. RLGM maintains safe regions and reduces gradient variance for intended training and this provides a better accuracy of the learning goal. In addition, RLGM achieves prompt training progress and selects precisely the series of parameters required by the network during the training phase. RLGM produces spontaneous derivation of the essential deep network scale over the training process drawing on automatically unvarying trained weights. Our proposed approach outperforms other reinforcement learning methods such as Federated RL, Deep Q Learning (DQL), in addition to non-machine learning based techniques such as GA-AOMDV.