HeartPrint: Passive Heart Sounds Authentication Exploiting In-Ear Microphones

Biometrics has been increasingly integrated into wearable devices to enhance data privacy and security in recent years. Meanwhile, the popularity of wearables in turn creates a unique opportunity for capturing novel biometrics leveraging various embedded sensing modalities. In this paper, we study a new intracorporal biometrics combining the uniqueness of i) heart motion, ii) bone conduction, and iii) body asymmetry. Specifically, we design HeartPrint as a passive yet secure user authentication system: it exploits the bone-conducted heart sounds captured by (widely available) dual in-ear microphones (IEMs) to authenticate users, while neatly leveraging IEMs renders itself transparent to users without impairing the normal functions of earphones. To suppress the interference from other body sounds and audio produced by the earphones, we develop a novel interference elimination method using modified non-negative matrix factorization to separate clean heart sounds from background interference. We further explore the uniqueness of IEM-recorded heart sounds in three aspects to extract a novel biometric representation, based on which HeartPrint leverages a convolutional neural model equipped with a continual learning method to achieve accurate authentication under drifting body conditions. Extensive experiments with 18 pairs of commercial earphones on 45 participants confirm that HeartPrint can achieve 1.6% FAR and 1.8% FRR, while effectively coping with major attacks, complicated interference, and hardware diversity.