Search for: All records

Urban air mobility (UAM) has become a potential candidate for civilization for serving smart citizens, such as through delivery, surveillance, and air taxis. However, safety concerns have grown since commercial UAM uses a publicly available communication infrastructure that enhances the risk of jamming and spoofing attacks to steal or crash crafts in UAM. To protect commercial UAM from cyberattacks and theft, this work proposes an artificial intelligence (AI)-enabled exploratory cyber-physical safety analyzer framework. The proposed framework devises supervised learning-based AI schemes such as decision tree, random forests, logistic regression, K-nearest neighbors (KNN), and long short-term memory (LSTM) for predicting and detecting cyber jamming and spoofing attacks. Then, the developed framework analyzes the conditional dependencies based on the Pearson’s correlation coefficient among the control messages for finding the cause of potential attacks based on the outcome of the AI algorithm. This work considers the UAM attitude control scenario for determining jam and spoofing attacks as a use case to validate the proposed framework with a state-of-the-art UAV attack dataset. The experiment results show the efficacy of the proposed framework in terms of around 99.9% accuracy for jamming and spoofing detection with a decision tree, random forests, and KNN while efficiently finding the root cause of the attack.