More Like this

1. A Proposed Framework for UAS Positioning in GPS-Denied and GPS-Spoofed Environments

   https://doi.org/10.1109/ICNS60906.2024.10550601  

   Burbank, Jack L; Foust, Landon; Greene, Trevor; Kaabouch, Naima (April 2024, IEEE)

   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 » « less
2. Tree-based Supervised Machine Learning Models For Detecting GPS Spoofing Attacks on UAS

   https://doi.org/10.1109/UEMCON53757.2021.9666744  

   Aissou, Ghilas; Slimane, Hadjar Ould; Benouadah, Selma; Kaabouch, Naima (December 2021, IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference)

   The security of Unmanned Aerial System (UAS) networks is becoming crucial as their number and application in several fields are increasing every day. For navigation and positioning, the Global Navigation System (GPS) is essential as it provides an accurate location for the UAS. However, since the civilian GPS signals are open and unencrypted, attackers target them in different ways such as spoofing attacks. To address this security concern, we propose a comparison of several tree-based machine learning models, namely Random Forest, Gradient Boost, XGBoost, and LightGBM, to detect GPS spoofing attacks. In this work, the dataset was built of real GPS signals that were collected using a Software Defined Radio unit and different types of simulated GPS spoofing attacks. The results show that XGBoost has the best accuracy (95.52%) and fastest detection time (2ms), which makes this model appropriate for UAS applications. 

   more » « less
3. Instance-based Supervised Machine Learning Models for Detecting GPS Spoofing Attacks on UAS

   https://doi.org/10.1109/CCWC54503.2022.9720888  

   Aissou, Ghilas; Benouadah, Selma; El Alami, Hassan; Kaabouch, Naima (January 2022, IEEE Annual Computing and Communication Workshop and Conference (CCWC))

   Unmanned Aerial Systems (UAS) heavily depend on the Global Positioning System (GPS) for navigation. However, the unencrypted civilian GPS signals are subject to different types of threats, including GPS spoofing attacks. In this paper, we evaluate five instance-based learning models for GPS spoofing detection in UAS, namely K Nearest Neighbor, Radius Neighbor, Linear Support Vector Machine (SVM), C-SVM, and Nu-SVM. We used software-defined radio units to collect and extract features from satellite signals. Then, we simulated three types of GPS spoofing attacks specifically the simplistic, intermediate, and sophisticated attacks. The evaluation results show that Nu-SVM outperforms the other instance learning classifiers in terms of accuracy, probability of detection, probability of false alarm, and probability of misdetection. In addition, the model shows good computational performance regarding memory usage and processing time in the detection phase. 

   more » « less
4. HEROES: Humanitarian Emergency Response based on UAV-enabled Integrated Sensing and Communication, Positioning, and Satisfaction Games

   https://doi.org/10.1145/3715334  

   Siraj, Md Sadman; Charatsaris, Panagiotis; Diamanti, Maria; Tsiropoulou, Eirini Eleni; Papavassiliou, Symeon (December 2025, ACM Journal on Autonomous Transportation Systems)

   In the field of autonomous transportation systems, the integration of Unmanned Aerial Vehicles (UAVs) in emergency response scenarios is important for enhancing the operational efficiency and the victims’ positioning. This article presents a novel Positioning, Navigation, and Timing (PNT) framework, namedHEROES, which leverages the UAV and integrated sensing and communication technologies to address the challenges in post-disaster environments. Our approach focuses on a comprehensive post-disaster scenario involving multiple victims, first responders, UAVs, and an emergency control center. HEROES enables UAVs to function as anchor nodes and facilitate the precise positioning of the victims while simultaneously collecting critical data from the disaster area. We further introduce a reinforcement learning model based on the Optimistic Q-learning with Upper Confidence Bound algorithm, enabling the victims and first responders to autonomously select the most advantageous UAV connections based on their channel gain, shadowing probability, and positional characteristics. Furthermore, HEROES is based on a satisfaction game-theoretic model to enhance the sensing, communication, and positioning functionalities. Our analysis reveals the existence of various satisfaction equilibria, including minimum efficient satisfaction equilibrium, ensuring that the UAVs meet their quality of service constraints at minimal operational costs. Extensive experimental results validate the scalability and performance of HEROES, demonstrating significant improvements over existing state-of-the-art methods in delivering PNT services during humanitarian emergencies. 

   more » « less
5. A Reinforcement Learning Approach for Global Navigation Satellite System Spoofing Attack Detection in Autonomous Vehicles

   https://doi.org/10.1177/03611981221095509  

   Dasgupta, Sagar; Ghosh, Tonmoy; Rahman, Mizanur (December 2022, Transportation Research Record: Journal of the Transportation Research Board)

   A resilient positioning, navigation, and timing (PNT) system is a necessity for the robust navigation of autonomous vehicles (AVs). A global navigation satellite system (GNSS) provides satellite-based PNT services. However, a spoofer can tamper the authentic GNSS signal and could transmit wrong position information to an AV. Therefore, an AV must have the capability of real-time detection of spoofing attacks related to PNT receivers, whereby it will help the end-user (the AV in this case) to navigate safely even if the GNSS is compromised. This paper aims to develop a deep reinforcement learning (RL)-based turn-by-turn spoofing attack detection method using low-cost in-vehicle sensor data. We have utilized the Honda Research Institute Driving Dataset to create attack and non-attack datasets to develop a deep RL model and have evaluated the performance of the deep RL-based attack detection model. We find that the accuracy of the deep RL model ranges from 99.99% to 100%, and the recall value is 100%. Furthermore, the precision ranges from 93.44% to 100%, and the f1 score ranges from 96.61% to 100%. Overall, the analyses reveal that the RL model is effective in turn-by-turn spoofing attack detection. 

   more » « less