Aircraft Fingerprinting Using Deep Learning
Alessandro Nicolussi, Simon Tanner, Roger P. Wattenhofer · 2020
Aircraft periodically broadcast their position, identity and other information using the ADS-B protocol. This allows safe air traffic flow as ground stations and other aircraft can depend on the sent information. However, these messages are not authenticated or encrypted. Therefore, this system is vulnerable to attacks from Software Defined Radios (SDRs) and other transmitters. We propose a deep learning-based approach for fingerprinting of aircraft messages based on physical characteristics. This helps to verify the origin of an observed message.