Type
Text
Type
Thesis
Advisor
Committee members: Das, Samir, R.; Rahmati, Amir; Polychronakis, Michalis; Nagendra, Vasudevan
Date
2020-05-01
Keywords
Device Activity Detection, Internet of Things, Smart Home, Traffic Signatures
Department
Department of Computer Science
Language
en
Source
This work is sponsored by the Stony Brook University Graduate School in compliance with the requirements for completion of degree.
Identifier
https://hdl.handle.net/11401/79109
Publisher
The Graduate School, Stony Brook University: Stony Brook, NY.
Format
application/pdf
Abstract
The popularity of the Internet of Things (IoT), smart home devices specifically, has been tremendous in the past couple of years. Devices like smart speakers, smart fridge, etc. have integrated seamlessly with the lives of homeowners. The main reasons being their accessibility, cost-effectiveness, and energy-efficiency. These devices by nature, continuously communicate with each other and their servers, to automate the day-to-day activities for their owners and in the process generate huge amounts of network traffic. But at the same time, this underlying automation can often occlude the operation and communication between devices from their owners. This thesis is a step towards understanding the causation of smart-home activities, thereby increasing the visibility and transparency in a smart home. In this thesis, we use the network traffic traces to generate packet-level traffic signatures for device activities (change speaker volume, play music, turn ON lights), which can help identify the triggering devices for an observed activity in a smart home, without causing significant computational overhead or storage constraints. By signature matching, we show how the triggering device can be identified by the users. We present our results on our IoT testbed (WINGS Lab in Stony Brook University) and publicly available datasets. We demonstrate that our approach can identify activities and corresponding sources with good accuracy. | 39 pages
Recommended Citation
Alatkar, Sayali Anil, "Detecting Smart Home Activity Through Network Traffic Signatures" (2020). Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions). 3972.
https://commons.library.stonybrook.edu/stony-brook-theses-and-dissertations-collection/3972