Biometric identification system based on object interactions in Internet of Things environments

Conference item

Attributing interactions with Internet of Things (IoT) devices to specific users in smart environments is extremely important as it enables personalized configurations and access control. This requirement is particularly stringent when it comes to parental control measures designed to protect children from contact with dangerous machinery or viewing materials that are inappropriate for their age. To this end, we show that naturally occurring interactions with objects in smart environments can be used as a behavioral biometric in order to identify users. The heterogeneous nature of smart devices enables the collection of a wide variety of inputs from such interactions. In addition, this system model allows for seamless identification, without the need for active user participation or rearrangement of the IoT devices. We conduct a remote study taking place in six households composed of 25 participants. We demonstrate that our system can identify users in multi-user environments with an average accuracy of at least 91% for a single object interaction without requiring any sensors on the object itself. This accuracy rises to 100% when six or more consecutive interactions are considered.

Authors: Krawiecka, K; Birnbach, S; Eberz, S; Martinovic, I

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Pages: 215-221
• Publication date: 2022-05-26
• Acceptance date: 2022-03-14
• Event title: IEEE Workshop on the Internet of Safe Things: SafeThings 2022
• Event location: San Francisco, California, USA
• Event website: https://safe-things-2022.github.io/
• Event start date: 2022-05-26
• Event end date: 2022-05-26
• DOI: 10.1109/SPW54247.2022.9833878
• EISSN: 2770-8411
• ISSN: 2639-7862
• Language: English
• Keywords: FFR