GOTCHA: Physical Intrusion Detection with Active Acoustic Sensing Using a Smart Speaker

Hoang Quoc Viet Pham, Hoang D. Nguyen, Utz Roedig

Abstract: Voice Assistants (VAs) in the form of smart speakers such as Amazon Alexa, Google Assistant or Apple Siri are now commonplace. Due to their ubiquitous presence they can be useful as home alarm systems. In this work we present the development and evaluation of a novel physical intrusion detection system GOTCHA based on human presence detection with active acoustic sensing. GOTCHA can execute on simple off-the-shelf smart speaker hardware. Periodic audible chirps are employed to gather data which are then processed by a deep autoencoder trained on the acoustic profile of the empty room. As our evaluation shows, GOTCHA achieves promising results of up to 99.2% for the F1-score. Our experiments show that a person can be detected without fail while the system barely generates false alarms. GOTCHA is a viable alternative to passive sensing solutions for physical intrusion detection.