skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 5:00 PM ET until 11:00 PM ET on Friday, June 21 due to maintenance. We apologize for the inconvenience.

Title: Detecting GNSS spoofing using deep learning

Global Navigation Satellite System (GNSS) is pervasively used in position, navigation, and timing (PNT) applications. As a consequence, important assets have become vulnerable to intentional attacks on GNSS, where of particular relevance is spoofing transmissions that aim at superseding legitimate signals with forged ones in order to control a receiver’s PNT computations. Detecting such attacks is therefore crucial, and this article proposes to employ an algorithm based on deep learning to achieve the task. A data-driven classifier is considered that has two components: a deep learning model that leverages parallelization to reduce its computational complexity and a clustering algorithm that estimates the number and parameters of the spoofing signals. Based on the experimental results, it can be concluded that the proposed scheme exhibits superior performance compared to the existing solutions, especially under moderate-to-high signal-to-noise ratios.

more » « less
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
Springer Science + Business Media
Date Published:
Journal Name:
EURASIP Journal on Advances in Signal Processing
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. 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
  2. In Global Navigation Satellite System (GNSS), a spoofing attack consists of forged signals which possibly cause the attacked receivers to deduce a false position, a false clock, or both. In contrast to simplistic spoofing, the induced spoofing captures the victim tracking loops by gradually adjusting it’s parameters, e.g., code phase and power. Then the victims smoothly deviates from the correct position or timing. Therefore, it is more difficult to detect the induced spoofing than the simplistic one. In this paper, by utilizing the dynamic nature of such gradual adjustment process, an induced spoofing detection method is proposed based on the S-curve-bias (SCB). Firstly, SCB in the inducing process is theoretically derived. Then, in order to detect the induced spoofing, a detection metric is defined. After that, a series of experiments using the Texas spoofing test battery (TEXBAT) are performed to demonstrate the effectiveness of the proposed algorithm. 
    more » « less
  3. 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
  4. 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
  5. Unmanned aerial vehicles (UAVs) must keep track of their location in order to maintain flight plans. Currently, this task is almost entirely performed by a combination of Inertial Measurement Units (IMUs) and reference to GNSS (Global Navigation Satellite System). Navigation by GNSS, however, is not always reliable, due to various causes both natural (reflection and blockage from objects, technical fault, inclement weather) and artificial (GPS spoofing and denial). In such GPS-denied situations, it is desirable to have additional methods for aerial geolocalization. One such method is visual geolocalization, where aircraft use their ground facing cameras to localize and navigate. The state of the art in many ground-level image processing tasks involve the use of Convolutional Neural Networks (CNNs). We present here a study of how effectively a modern CNN designed for visual classification can be applied to the problem of Absolute Visual Geolocalization (AVL, localization without a prior location estimate). An Xception based architecture is trained from scratch over a >1000 km2 section of Washington County, Arkansas to directly regress latitude and longitude from images from different orthorectified high-altitude survey flights. It achieves average localization accuracy on unseen image sets over the same region from different years and seasons with as low as 115 m average error, which localizes to 0.004% of the training area, or about 8% of the width of the 1.5 × 1.5 km input image. This demonstrates that CNNs are expressive enough to encode robust landscape information for geolocalization over large geographic areas. Furthermore, discussed are methods of providing uncertainty for CNN regression outputs, and future areas of potential improvement for use of deep neural networks in visual geolocalization. 
    more » « less