Detecting Cyber-Physical Attacks in Additive Manufacturing using Digital Audio Signing

Abstract

Additive Manufacturing (AM, or 3D printing) is a novel manufacturing technology that is being adopted in industrial and consumer settings. However, the reliance of this technology on computerization has raised various security concerns. In this paper we address sabotage via tampering with the 3D printing process. We present an object verification system using side-channel emanations: sound generated by onboard stepper motors. The contributions of this paper are following. We present two algorithms: one which generates a master audio fingerprint for the unmodified printing process, and one which computes the similarity between other print recordings and the master audio fingerprint. We then evaluate the deviation due to tampering, focusing on the detection of minimal tampering primitives. By detecting the deviation at the time of its occurrence, we can stop the printing process for compromised objects, thus save time and prevent material waste. We discuss impacts on the method by aspects like background noise, or different audio recorder positions. We further outline our vision with use cases incorporating our approach.