Search for: All records

Unmanned Aerial Vehicles (UAVs) are prone to cyber threats, including Global Positioning System (GPS) spoofing attacks. Several studies have been performed to detect and classify these attacks using machine learning and deep learning techniques. Although these studies provide satisfactory results, they deal with several limitations, including limited data samples, high costs of data annotations, and investigation of data patterns. Unsupervised learning models can address these limitations. Therefore, this paper compares the performance of four unsupervised deep learning models, namely Convolutional Auto Encoder, Convolutional Restricted Boltzmann Machine, Deep Belief Neural Network, and Adversarial Neural Network in detecting GPS spoofing attacks on UAVs. The performance evaluation of these models was done in terms of Gap static, Calinski harabasz score, Silhouette Score, homogeneity, completeness, and V-measure. The results show that the Convolutional Auto-Encoder has the best performance results among the other unsupervised deep learning models. 

The Automatic Dependent Surveillance Broadcast (ADS-B) system is a critical communication and surveillance technology used in the Next Generation (NextGen) project as it improves the accuracy and efficiency of air navigation. These systems allow air traffic controllers to have more precise and real-time information on the location and movement of aircraft, leading to increased safety and improved efficiency in the airspace. While ADS-B has been made mandatory for all aircraft in the Federal Aviation Administration (FAA) monitored airspace, its lack of security measures leaves it vulnerable to cybersecurity threats. Particularly, ADS-B signals are susceptible to false data injection attacks due to the lack of authentication and integrity measures, which poses a serious threat to the safety of the National Airspace System (NAS). Many studies have attempted to address these vulnerabilities; however, machine learning and deep learning approaches have gained significant interest due to their ability to enhance security without modifying the existing infrastructure. This paper investigates the use of Recurrent Neural Networks for detecting injection attacks in ADS-B data, leveraging the time-dependent nature of the data. The paper reviews previous studies that used different machine learning and deep learning techniques and presents the potential benefits of using RNN algorithms to improve ADS-B security. 

Unmanned Aerial Networks (UAVs) are prone to several cyber-attacks, including Global Positioning Spoofing attacks. For this purpose, numerous studies have been conducted to detect, classify, and mitigate these attacks, using Artificial Intelligence techniques; however, most of these studies provided techniques with low detection, high misdetection, and high bias rates. To fill this gap, in this paper, we propose three supervised deep learning techniques, namely Deep Neural Network, U Neural Network, and Long Short Term Memory. These models are evaluated in terms of Accuracy, Detection Rate, Misdetection Rate, False Alarm Rate, Training Time per Sample, Prediction Time, and Memory Size. The simulation results indicated that the U Neural Network outperforms other models with an accuracy of 98.80%, a probability of detection of 98.85%, a misdetection of 1.15%, a false alarm of 1.8%, a training time per sample of 0.22 seconds, a prediction time of 0.2 seconds, and a memory size of 199.87 MiB. In addition, these results depicted that the Long Short-Term Memory model provides the lowest performance among other models for detecting these attacks on UAVs. 

Unmanned Aerial Vehicles have been widely used in military and civilian areas. The positioning and return-to-home tasks of UAVs deliberately depend on Global Positioning Systems (GPS). However, the civilian GPS signals are not encrypted, which can motivate numerous cyber-attacks on UAVs, including Global Positioning System spoofing attacks. In these spoofing attacks, a malicious user transmits counterfeit GPS signals. Numerous studies have proposed techniques to detect these attacks. However, these techniques have some limitations, including low probability of detection, high probability of misdetection, and high probability of false alarm. In this paper, we investigate and compare the performances of three ensemble-based machine learning techniques, namely bagging, stacking, and boosting, in detecting GPS attacks. The evaluation metrics are the accuracy, probability of detection, probability of misdetection, probability of false alarm, memory size, processing time, and prediction time per sample. The results show that the stacking model has the best performance compared to the two other ensemble models in terms of all the considered evaluation metrics. 

Advances made in Unmanned Aircraft Vehicles (UAVs) have increased rapidly in the last decade resulting in new applications in both civil and military spheres. However, with the growth in the usage of these systems, various cybersecurity challenges arose unveiling the vulnerabilities of UAV wireless networks. Among the attacks that threaten the network's availability and reduce their performance are jamming attacks. Several approaches have been proposed to address this problem; however, most of them are not suitable for UAVs due to their reduced size, weight, and power constraints. In this paper, we propose a lightweight machine learning technique, LightGBM, to detect deceptive jamming attacks on UAV networks. The performance of this model is compared to that of three boosting and bagging-based machine learning models namely, XGBoost, Gradient Boost, and Random Forest. The results show that, although the LightGBM model has slightly lower accuracy (98.4%) than Gradient Boost (99%) and Random Forest (98.87%), it is 21 times faster and occupies two times less memory during the prediction than Gradient Boost and Random Forest.