In Air Traffic Management (ATM) training, simulations of real air traffic control (ATC) scenarios are a key part of practical teaching. On the internet one may find multiple different ATM simulators available to the public with open source code. Today most aircraft transmit data about position, altitude, and speed into the atmosphere that essentially are unencrypted data points, available to the public. This means that potential attackers could project "fake" ADS-B data and spoof existing data to the air traffic controllers (ATCO) if the right equipment is used. We see this as a security flaw and we want to prepare ATCO for cyberattacks by modifying an ATM simulator with cyberattacks. First, openScope was chosen as the ATM simulator to be modified. Subsequently, three types of attacks were chosen for the simulator to be equipped with, based on ADS-B weaknesses from existing literature: aircraft that do not respond to commands, aircraft with altering positional data, and aircraft with incorrect speed and altitude data. The recorded parameters were the written command lines and corresponding aircraft type it was applied to. Using this modified simulator, ATCO can now be evaluated against cyberattacks. / Inom utbildningen till att bli flygledare finns olika simuleringar av verkliga scenarion och det är en viktig del av lärandet. Idag finns det många olika flygledningssimulatorer som finns tillgängliga för allmänheten med öppen källkod på internet. Idag sänder de flesta flygplan information om position, höjd och hastighet ut i atmosfären som i själva verket är okrypterade datapunkter och är tillgängliga för vem som helst som har rätt teknik tillgänglig. Det är även möjligt att både skicka och ändra denna data. Vi ser detta som en stor säkerhetsbrist och vill förbereda flygledare för olika former av cyberattacker genom att modifiera en tillgänglig simulator. Först valdes simulatorn openScope till att modifieras. Härnäst valdes tre olika former av attacker: flygplan som inte ger svar på kommandon, flygplan som spontant byter position och flygplan som visar felaktig höjd och hastighet. För att analysera användaren valdes det att spara använderans kommandon och attacksorten av flygplanet i fråga. Med hjälp av denna simulator kan flygledare nu utvärderas på deras hantering av cyberattacker.

In a time where general technology is progressing at a rapid rate, this thesis aims to present possible advancements to security in regard to air traffic communication. By highlighting how data can be extracted using simple hardware and open-source software the transparency and lack of authentication is showcased. The research is specifically narrowed down to discovering vulnerabilities of the ADS-B protocol in order to apply countermeasures. Through fetching live aircraft data with OpenSky-Network and through fetching simulated ADS-B attack data with OpenScope, this thesis develops a data set with both authentic and malicious ADS-B messages. The data set was cleaned in order to remove outliers and other improper data. A machine learning model was later trained with the data set in order to detect malicious ADS-B messages. With the use of Support Vector Machine (SVM), it was possible to produce a model that can detect four different types of aviation communications attacks as well as allow authentic messages to pass through the IDS. The finished model was able to detect incoming ADS-B attacks with an overall accuracy of 83.10%.

Air traffic communication is one of the most vital systems for air traffic management controllers. It is used every day to allow millions of people to travel safely and efficiently across the globe. But many of the systems considered industry-standard are used without any sort of encryption and authentication meaning that they are vulnerable to different wireless attacks. In this thesis vulnerabilities within an air traffic management system called ADS-B will be investigated. The structure and theory behind this system will be described as well as the reasons why ADS-B is unencrypted. Two attacks will then be implemented and performed in an open-source air traffic management simulator called openScope. ADS-B data from these attacks will be gathered and combined with actual ADS-B data from genuine aircrafts. The collected data will be cleaned and used for machine learning purposes where three different algorithms will be applied to detect attacks. Based on our findings, where two out of the three machine learning algorithms used were able to detect 99.99% of the attacks, we propose that machine learning algorithms should be used to improve ADS-B security. We also think that educating air traffic controllers on how to detect and handle attacks is an important part of the future of air traffic management.