Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
-
NA (Ed.)Unmanned aerial vehicles (UAVs) are prone to several cyber-attacks, including global positioning system (GPS) spoofing. The use of machine learning and deep learning are becoming increasingly common for UAV GPS spoofing attack detection; however, these approaches have some limitations, such as a high rate of false alarm and misdetection. We propose using capsule networks to detect and classify UAV-focused GPS spoofing attacks. This paper compares simple capsule networks, efficient capsule networks, dual attention capsule networks, and convolutional neural network in terms of accuracy, probability of detection, probability of misdetection, probability of false alarm, prediction time, training time per sample, and memory size. The results indicate that the Efficient-capsule network outperforms the other models, as demonstrated by an accuracy of 99.1%, a probability of detection of 99.9%, a probability of misdetection of 0.1%, a probability of false alarm of 0.37%, a prediction time of 0.5 seconds, a training time per sample of 0.2 seconds, and a memory size of 123 mebibytes for binary classification.more » « lessFree, publicly-accessible full text available February 1, 2026
-
Modern systems and devices, including unmanned aerial systems (UAS), autonomous vehicles, and other unmanned and autonomous systems, commonly rely on the Global Positioning System (GPS) for positioning, navigation, and timing (PNT). Cellular mobile devices rely on GPS for PNT and location-based services. Many of these systems cannot function correctly without GPS; however, GPS signals are susceptible to a wide variety of signal-related disruptions and cyberattacks. GPS threat detection and mitigation have received significant attention recently. There are many surveys and systematic reviews in the literature related to GPS security; however, many existing reviews only briefly discuss GPS security within a larger discussion of cybersecurity. Other reviews focus on niche topics related to GPS security. There are no existing comprehensive reviews of GPS security issues in the literature. This paper fills that gap by providing a comprehensive treatment of GPS security, with an emphasis on UAS applications. This paper provides an overview of the threats to GPS and the state-of-the-art techniques for attack detection and countermeasures. Detection and mitigation approaches are categorized, and the strengths and weaknesses of existing approaches are identified. This paper also provides a comprehensive overview of the state-of-the-art on alternative positioning and navigation techniques in GPS-disrupted environments, discussing the strengths and weaknesses of existing approaches. Finally, this paper identifies gaps in existing research and future research directions.more » « lessFree, publicly-accessible full text available September 1, 2025
-
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.more » « lessFree, publicly-accessible full text available April 23, 2025
-
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.more » « lessFree, publicly-accessible full text available April 23, 2025
-
NA (Ed.)Unmanned Aerial Systems have become ubiquitous and are now widely used in commercial, consumer, and military applications. Their widespread use is due to a combination of their low cost, high capability, and ability to perform tasks and go places that are not easy or safe for humans. Most UAS platforms are dependent on Global Navigation Satellite Systems (GNSS), such as the Global Positioning System (GPS), to provide positioning information for navigation and flight control. Without reliable GPS signals, the flight path cannot be trusted, and flight safety cannot be assured. However, GPS is vulnerable to several types of malicious attacks, including jamming, spoofing, or physical attacks on the GPS constellation itself. Additionally, there are environments in which GPS reception is not always possible, a key example being urban canyon areas where line-of-site to the GPS satellite constellation may be blocked or obscured by large obstacles such as buildings. Numerous methods have been proposed for position estimation in GPS denied environments. However, these methods have significant limitations and typically exhibit poor performance in certain environments and scenarios. This paper analyzes the strengths and weaknesses of existing alternate positioning methods and describes a framework where multiple positioning solutions are jointly employed to construct an optimal position estimate. The proposed framework aims to reduce computation complexity and yield good positioning performance across a wide variety of environments.more » « lessFree, publicly-accessible full text available April 23, 2025
-
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.more » « less
-
In this paper, a three-class machine learning (ML) model is implemented on an unmanned aerial vehicle (UAV) with a Raspberry Pi processor for classifying two global positioning system (GPS) spoofing attacks (i.e., static, dynamic) in real-time. First, several models are developed and tested utilizing a dataset collected in a previous work. This dataset conveys GPS-specific features, including location information. Models evaluations are carried out using the detection rate, F-score, false alarm rate, and misdetection rate, which all showed an acceptable performance. Then, the optimum model is loaded to the processor and tested for real-time detection and classification. Location-dependent applications, such as fixed-route public transportations are expected to benefit from the methodology presented herein as the longitude, latitude, and altitude features are characterized in the developed model.more » « less
-
This work proposes the use of machine learning (ML) as a candidate for the detection of various types of message injection attacks against automatic dependent surveillance-broadcast (ADSB) messaging systems. Authentic ADS-B messages from a high-traffic area are collected from an open-source platform. These messages are combined with others imposing path modification, ghost aircraft injection, and velocity drift obtained from simulations. Then, ADS-B-related features are extracted from such messages and used to train different ML models for binary classification. For this purpose, authentic ADS-B data is considered as Class 1 (i.e., no attack), while the injection attacks are considered as Class 2 (i.e., presence of attack). The performance of the models is analyzed with metrics, including detection, misdetection, and false alarm rates, as well as validation accuracy, precision, recall, and Fl-score. The resulting models enable identifying the presence of injection attacks with a detection rate of 99.05%, and false alarm and misdetection rates of 0.76% and 1.10%, respectively.more » « less
-
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.more » « less