Tree-based Supervised Machine Learning Models For Detecting GPS Spoofing Attacks on UAS

Aissou, Ghilas; Slimane, Hadjar Ould; Benouadah, Selma; Kaabouch, Naima

doi:10.1109/uemcon53757.2021.9666744

Cited by 32 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Aissou et al [111] compared several tree-based machine learning models, Random Forest (RNF), Gradient Boost (GB), XB, and LightBM (LB), to detect GPS Spoofing attacks. The datasets were generated from real-time GPS signals using a USRP device and simulated spoofed GPS signals by manipulating various features of authentic signals (e.g., Carrier-to-Noise Ratio, Time of the Week, etc.).…”

Section: B Gps Spoofing Defense Mechanisms In Uavsmentioning

confidence: 99%

See 1 more Smart Citation

GPS Spoofing Attacks in FANETs: A Systematic Literature Review

Altaweel,

Mukkath,

Kamel

2023

IEEE Access

View full text Add to dashboard Cite

Flying Ad-Hoc Networks (FANETs) are groups of UAVs connected in an Ad-Hoc manner to accomplish a common mission. The widespread acceptance of UAVs due to their low cost and high efficiency has attracted malicious security attacks against them. These attacks cannot be easily prevented due to UAVs' limited computational power, short battery life, and inability to execute complex algorithms. FANETs rely on the Global Positioning System (GPS) for localization. GPS Spoofing, an easy-to-launch attack, is one of the main challenges in FANETs. In which, the legitimate and not-encrypted civilian GPS signals are overridden by counterfeit signals to deceive the UAVs to collide or to be hijacked. Researchers proposed various countermeasures to address GPS Spoofing attacks in FANETs. To further assist future research, this paper provides a systematic literature review on GPS Spoofing attacks in FANETs and their defense mechanisms. After formulating eight research questions and applying well-defined inclusion/exclusion criteria and quality assessment tools, 70 research articles were extracted. The existing defense mechanisms were classified based on their objectives (i.e., detection, mitigation, and/or prevention) and according to their basis (i.e., relying on readings from various drones' devices/sensors, processing the signals received by various sensors, employing machine learning algorithms, relying on game theory, or leveraging cryptographic techniques to authenticate and protect the confidentiality of GPS signals). The defense mechanisms were also analyzed to identify the attacker models, impacts of the attack, and detection performance. This study found that most of the proposed methods are detection approaches, rather than mitigation or prevention. Also, almost all papers used simulation experiments rather than a proof-of-concept implementation, which does not demonstrate a convincing performance under realistic mobility and propagation models. Moreover, most solutions addressed GPS Spoofing for a single UAV. Only eight articles addressed multiple UAV scenarios and none of them provided a proof-of-concept evaluation. INDEX TERMSDrones, unmanned ariel vehicle (UAV), Flying Ad-Hoc NETwork (FANET), GPS spoofing attack, wireless network security, systematic literature review. * Spoofing tools such as simulators, repeaters, etc. * Spoofing techniques such as position denial and track break. * Spoofer location such as remote, onboard, and escort. --Defense mechanisms against GPS Spoofing: the research articles that discuss various mechanisms to defend against GPS Spoofing attacks in UAVs. These articles are further classified based on their objectives as follows: * Detection of GPS Spoofing attacks. * Mitigation the damage caused by GPS Spoofing attacks. * Prevention of GPS Spoofing. The defense mechanisms are also classified according to their basis as follows: * The use of devices/sensors on the drones. * Signal processing techniques applied on various signals received by various sensors on the drone. * Cryptographic techn...

show abstract

Section: B Gps Spoofing Defense Mechanisms In Uavsmentioning

confidence: 99%

“…), and Stacking (St.). The datasets were generated using the same approach in [111]. The performance of the models was evaluated in terms of Accuracy, probability of detection/misdetection, probability of false alarm, memory size, processing time, and prediction time per sample.…”

Section: B Gps Spoofing Defense Mechanisms In Uavsmentioning

confidence: 99%

GPS Spoofing Attacks in FANETs: A Systematic Literature Review

Altaweel,

Mukkath,

Kamel

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Анализ методов и алгоритмов обнаружения спуфинговых атак с использованием генераторов данных. В статье [7] В статьях [10,11] авторы описывают следующую схему для сбора данных как в случае, когда атака не проводится, так и в случае, когда атака проводится. Используются аппаратное обеспечение, которое представляет собой универсальное периферийное устройство с программно определяемым радио (SDR), и программное обеспечение GNSS-SDR с открытым исходным кодом на основе лицензии GNU.…”

Section: рис 1 схема влияния атаки на бпла и взаимосвязь с инцидентам...unclassified

“…Авторы используют два варианта нормализации данных, которые собраны в результате эксперимента. Первый вариант описан в статье [10] и включает в себя вычисление коэффициента корреляции Спирмена и модификацию нестационарных данных. Во втором исследовании авторы меняют способ нормализации и вычисляют коэффициент по методу корреляции Спирмена после применения минимаксных технологий.…”

Section: рис 1 схема влияния атаки на бпла и взаимосвязь с инцидентам...unclassified

Data Generation for Modeling Attacks on UAVs for the Purpose of Testing Intrusion Detection Systems

Basan¹,

Peskova²,

Silin³

et al. 2022

View full text Add to dashboard Cite

Today, issues related to ensuring the safety of UAVs are very relevant. Researchers need to develop new protection methods to detect attacks in a timely manner and implement mitigation measures. The authors propose a new concept of attack detection "from inside" the UAV. The idea is to analyze the cyber-physical parameters of the UAV, which may indicate an attack, and its possible consequences. It was determined that to detect an attack and determine the consequences to which it can lead, it is necessary to control not only the initial parameters, but also the internal cyber-physical parameters of the UAV. This will allow predicting the possible consequences of an attack and taking emergency measures. A scheme of the impact of an attack on UAVs and the relationship with security incidents, built using an ontological approach, has been worked out. Two main essences of the UAV are considered - the physical and digital aspects of the UAV. Examples of chains of attacks leading to various consequences are also shown. In the review part, the analysis of methods and algorithms for detecting spoofing attacks using data generators is carried out, based on which conclusions are drawn about their advantages and disadvantages. Further, based on the experiments performed, the authors propose a method for assessing the quality of data and a method for generating anomalous data sets similar to real attack data, which can be used to develop and test methods for detecting and blocking attacks. The architecture of the experimental stand, which was used in the framework of full-scale simulation, is described. At this stand, designed to parse GPS spoofing attacks (GPS spoofing), several scenarios of a normal flight, and then several attack scenarios, were tested. Based on the results of the experiments, a method has been proposed that allows simulating the data corresponding to the attack with the required accuracy. A method for assessing the quality of fake data has also been proposed.

show abstract

“…Aissou et al demonstrated the collection of data when attacks do and do not occur [13,14]. The hardware that was used was a Universal Software Radio Peripheral (USRP).…”

mentioning

confidence: 99%

A Data Normalization Technique for Detecting Cyber Attacks on UAVs

Basan

Nekrasov

et al. 2022

Drones

View full text Add to dashboard Cite

The data analysis subsystem of an Unmanned Aerial Vehicle (UAV) includes two main modules: a data acquisition module for data processing and a normalization module. One of the main features of an adaptive UAV protection system is the analysis of its cyber-physical parameters. An attack on a general-purpose computer system mainly affects the integrity, confidentiality and availability of important information. By contrast, an attack on a Cyber-Physical System (CPS), such as a UAV, affects the functionality of the system and may disrupt its operation, ultimately preventing it from fulfilling its tasks correctly. Cyber-physical parameters are the internal parameters of a system node, including the states of its computing resources, data storage, actuators and sensor system. Here, we develop a data normalization technique that additionally allows us to identify the signs of a cyber-attack. In addition, we define sets of parameters that can highlight an attack and define a new database format to support intrusion detection for UAVs. To achieve these goals, we performed an experimental study of the impact of attacks on UAV parameters and developed a software module for collecting data from UAVs, as well as a technique for normalizing and presenting data for detecting attacks on UAVs. Data analysis and the evaluation of the quality of a parameter (whether the parameter changes normally, or abrupt anomalous changes are observed) are facilitated by converting different types of data to the same format. The resulting formalized CPS model allows us to identify the nature of an attack and its potential impact on UAV subsystems. In the future, such a model could be the basis of a CPS digital twin in terms of security. The presented normalization technique supports processing raw data, as well as classifying data sets for their use in machine learning (ML) analyses in the future. The data normalization technique can also help to immediately determine the presence and signs of an attack, which allows classifying raw data automatically by dividing it into different categories. Such a technique could form the basis of an intrusion detection system for CPSs. Thus, the obtained results can be used to classify attacks, including attack detection systems based on machine learning methods, and the data normalization technique can be used as an independent method for detecting attacks.

show abstract

Tree-based Supervised Machine Learning Models For Detecting GPS Spoofing Attacks on UAS

Cited by 32 publications

References 18 publications

GPS Spoofing Attacks in FANETs: A Systematic Literature Review

GPS Spoofing Attacks in FANETs: A Systematic Literature Review

Data Generation for Modeling Attacks on UAVs for the Purpose of Testing Intrusion Detection Systems

A Data Normalization Technique for Detecting Cyber Attacks on UAVs

Contact Info

Product

Resources

About