Turning Noises to Fingerprint-Free "Credentials": Secure and Usable Authentication for Drone Delivery

Drone delivery is an emerging service that gains growing attention. Authentication is critical to ensure a package is picked up by a legitimate drone (rather than a malicious one) and delivered to the correct receiver (rather than an attacker). As delivery drones are expensive and may carry important packages, a drone should stay away from users until the authentication succeeds. Thus, authentication approaches that require physical contact of drones cannot be applied. Bluetooth can indicate proximity without physical contact but is vulnerable to radio relay attacks. Our work leverages drone noises for authentication. While using sounds for authentication is highly usable, how to handle various attacks that manipulate sounds is an unresolved challenge. It is also unclear whether such a system is robust under various environmental sounds. We address these challenges by exploiting unique characteristics of drone noises. We thereby build an authentication system that does not rely on any sound fingerprints, keeps resilient to attacks, and is robust under environmental sounds. An extensive evaluation demonstrates its security and usability.