Abstract
The traditional polygraph instrument is used worldwide for lie detection tests. It is currently used broadly in the civil sector, terrorism investigations, and criminal cases. In this paper, we introduce a novel concept of conducting lie detection tests with modern wearable devices. Unlike traditional polygraph instruments, wearable devices are easier and more accessible to use. This allows the test to be conducted in various environments, under flexible conditions, and is much cheaper. Our study consists of a comprehensive assessment of modern wearable devices for lie detection, employing the Guilty Knowledge Test (GKT) protocol. We also compared its effectiveness to that of a traditional polygraph instrument. In order to achieve our goal, we administered laboratory polygraph tests on 30 individuals, where we staged a 'mock crime' as a preliminary step. We built a data acquisition system along with a sequence of signal-processing steps for the examined devices. We have also developed an algorithm (AUTOMATED-KEY-FINDER) that simulates the human decision-making process for determining the final decision in polygraph tests. Our research results demonstrate that modern wearable devices can be used to detect lies in the GKT protocol. We show that this ability is comparatively weaker than that of a conventional polygraph instrument.
Original language | American English |
---|---|
Pages (from-to) | 7478-7491 |
Number of pages | 14 |
Journal | IEEE Transactions on Information Forensics and Security |
Volume | 19 |
DOIs | |
State | Published - 1 Jan 2024 |
Keywords
- Guilty Knowledge Test (GKT)
- Polygraph
- lie detection
- smartwatch
- wearable
All Science Journal Classification (ASJC) codes
- Safety, Risk, Reliability and Quality
- Computer Networks and Communications