This repository contains the codebase for the Zero-Interaction Security research project published in "Perils of Zero-Interaction Security in the Internet of Things", by Mikhail Fomichev, Max Maass, Lars Almon, Alejandro Molina, Matthias Hollick, in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 3, Issue 1, 2019.
The relevant datasets can be found on Zenodo.
The code in this repository is structured in several folders:
- DataCollection contains scripts and apps used for data collection with different platforms such a Raspeberry Pi with an attached SensorTag and a USB microphone, a Rapsberry Pi with a RuuviTag, Samsung Gear S3 smartwatch and Android smartphones.
- Postrocessing contains scripts to generate intermediate results such as machine learning datasets.
- Preprocessing contains scripts used to process the raw data before it is used in the different schemes. This includes features such as outlier removal, pseudonymization or structuring data.
- Schemes contains the implementations of the different zero-interaction security schemes.
- Visualization contains code to produce graphics used in the paper, as well as visuazliations generated by the evaluation code.
All code is licensed under the GNU GPLv3, unless noted otherwise. See LICENSE.txt for details.