Search for: All records

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. 

GPS spoofing attacks are a severe threat to unmanned aerial vehicles. These attacks manipulate the true state of the unmanned aerial vehicles, potentially misleading the system without raising alarms. Several techniques, including machine learning, have been proposed to detect these attacks. Most of the studies applied machine learning models without identifying the best hyperparameters, using feature selection and importance techniques, and ensuring that the used dataset is unbiased and balanced. However, no current studies have discussed the impact of model parameters and dataset characteristics on the performance of machine learning models; therefore, this paper fills this gap by evaluating the impact of hyperparameters, regularization parameters, dataset size, correlated features, and imbalanced datasets on the performance of six most commonly known machine learning techniques. These models are Classification and Regression Decision Tree, Artificial Neural Network, Random Forest, Logistic Regression, Gaussian Naïve Bayes, and Support Vector Machine. Thirteen features extracted from legitimate and simulated GPS attack signals are used to perform this investigation. The evaluation was performed in terms of four metrics: accuracy, probability of misdetection, probability of false alarm, and probability of detection. The results indicate that hyperparameters, regularization parameters, correlated features, dataset size, and imbalanced datasets adversely affect a machine learning model’s performance. The results also show that the Classification and Regression Decision Tree classifier has an accuracy of 99.99%, a probability of detection of 99.98%, a probability of misdetection of 0.2%, and a probability of false alarm of 1.005%, after removing correlated features and using tuned parameters in a balanced dataset. Random Forest can achieve an accuracy of 99.94%, a probability of detection of 99.6%, a probability of misdetection of 0.4%, and a probability of false alarm of 1.01% in similar conditions.