Date of Award

Spring 2021

Document Type

Thesis (Undergraduate)


Department of Computer Science

First Advisor

David Kotz

Second Advisor

Beatrice Perez


We are entering an era in which Smart Devices are increasingly integrated into our daily lives. Everyday objects are gaining computational power to interact with their environments and communicate with each other and the world via the Internet. While the integration of such devices offers many potential benefits to their users, it also gives rise to a unique set of challenges. One of those challenges is to detect whether a device belongs to one’s own ecosystem, or to a neighbor – or represents an unexpected adversary. An important part of determining whether a device is friend or adversary is to detect whether a device’s location is within the physical boundaries of one’s space (e.g. office, classroom, home). In this thesis we propose a system that is able to decide with 82% accuracy whether the location of an IoT device is inside or outside of a defined space based on a small number of transmitted Wi- Fi frames. The classification is achieved by leveraging a machine-learning classifier trained and tested on RSSI data of Wi-Fi transmissions recorded by three or more observers. In an initialization phase the classifier is trained by the user on Wi-Fi transmissions of a variety of locations, inside (and outside). The system can be built with off-the-shelf Wi-Fi observing devices that do not require any special hardware modifications. With the exception of the training period, the system can accurately classify the indoor/outdoor state of target devices without any cooperation from the user or from the target devices.