Hedgehog: Detecting Drink Spiking on Wearables

Zhigang Yin, Mohan Liyanage, Agustin Zuniga, Petteri Nurmi, Huber Flores

Abstract: People increasingly carry wearables and the capabilities of these devices have reached a point where it is increasingly possible to harness the devices to support everyday interactions. We contribute a new use of wearables by demonstrating how they can be used to safeguard against drink spiking, the deliberate act of adding substances to another person's drink. We design Hedgehog, a pervasive sensing approach that re-purposes the optical sensors in off-the-shelf wearables to identify spiked drinks by analysing differences in light reflectivity resulting from small particles inside the drink. We present a wearable prototype inspired by a smart ring design and conduct rigorous experiments that show the Hedgehog reaches up to 89.71% accuracy in detecting drinks that are tampered with. Our work demonstrates how pervasive sensing enables innovative applications and how smart wearables can be re-purposed to support personal safety.