Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity

As the concept of the Smart Home is being embraced globally, IoT devices such as the Amazon Echo, Google Home, and Nest Thermostat are becoming a part of more and more households. In the data-driven world we live in today, internet service providers (ISPs) and companies are collecting large amounts...

Full description

Bibliographic Details
Main Author: Hashemi, Arshan
Format: Others
Published: DigitalCommons@CalPoly 2018
Subjects:
IoT
Online Access:https://digitalcommons.calpoly.edu/theses/1958
https://digitalcommons.calpoly.edu/cgi/viewcontent.cgi?article=3336&context=theses
id ndltd-CALPOLY-oai-digitalcommons.calpoly.edu-theses-3336
record_format oai_dc
spelling ndltd-CALPOLY-oai-digitalcommons.calpoly.edu-theses-33362020-07-15T07:09:31Z Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity Hashemi, Arshan As the concept of the Smart Home is being embraced globally, IoT devices such as the Amazon Echo, Google Home, and Nest Thermostat are becoming a part of more and more households. In the data-driven world we live in today, internet service providers (ISPs) and companies are collecting large amounts of data and using it to learn about their customers. As a result, it is becoming increasingly important to understand what information ISPs are capable of collecting. IoT devices in particular exhibit distinct behavior patterns and specific functionality which make them especially likely to reveal sensitive information. Collection of this data provides valuable information and can have some serious privacy implications. In this work I present an approach to fingerprinting IoT devices behind private networks while only examining last-mile internet traffic . Not only does this attack only rely on traffic that would be available to an ISP, it does not require changes to existing infrastructure. Further, it does not rely on packet contents, and therefore works despite encryption. Using a database of 64 million packets logged over 15 weeks I was able to train machine learning models to classify the Amazon Echo Dot, Amazon Echo Show, Eufy Genie, and Google Home consistently. This approach combines unsupervised and supervised learning and achieves a precision of 99.95\%, equating to one false positive per 2,000 predictions. Finally, I discuss the implication of identifying devices within a home. 2018-12-01T08:00:00Z text application/pdf https://digitalcommons.calpoly.edu/theses/1958 https://digitalcommons.calpoly.edu/cgi/viewcontent.cgi?article=3336&context=theses Master's Theses and Project Reports DigitalCommons@CalPoly IoT Smart Assistants Machine Learning Fingerprinting IoT Privacy IoT Security
collection NDLTD
format Others
sources NDLTD
topic IoT
Smart Assistants
Machine Learning
Fingerprinting
IoT Privacy
IoT Security
spellingShingle IoT
Smart Assistants
Machine Learning
Fingerprinting
IoT Privacy
IoT Security
Hashemi, Arshan
Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity
description As the concept of the Smart Home is being embraced globally, IoT devices such as the Amazon Echo, Google Home, and Nest Thermostat are becoming a part of more and more households. In the data-driven world we live in today, internet service providers (ISPs) and companies are collecting large amounts of data and using it to learn about their customers. As a result, it is becoming increasingly important to understand what information ISPs are capable of collecting. IoT devices in particular exhibit distinct behavior patterns and specific functionality which make them especially likely to reveal sensitive information. Collection of this data provides valuable information and can have some serious privacy implications. In this work I present an approach to fingerprinting IoT devices behind private networks while only examining last-mile internet traffic . Not only does this attack only rely on traffic that would be available to an ISP, it does not require changes to existing infrastructure. Further, it does not rely on packet contents, and therefore works despite encryption. Using a database of 64 million packets logged over 15 weeks I was able to train machine learning models to classify the Amazon Echo Dot, Amazon Echo Show, Eufy Genie, and Google Home consistently. This approach combines unsupervised and supervised learning and achieves a precision of 99.95\%, equating to one false positive per 2,000 predictions. Finally, I discuss the implication of identifying devices within a home.
author Hashemi, Arshan
author_facet Hashemi, Arshan
author_sort Hashemi, Arshan
title Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity
title_short Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity
title_full Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity
title_fullStr Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity
title_full_unstemmed Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity
title_sort fingerprinting the smart home: detection of smart assistants based on network activity
publisher DigitalCommons@CalPoly
publishDate 2018
url https://digitalcommons.calpoly.edu/theses/1958
https://digitalcommons.calpoly.edu/cgi/viewcontent.cgi?article=3336&context=theses
work_keys_str_mv AT hashemiarshan fingerprintingthesmarthomedetectionofsmartassistantsbasedonnetworkactivity
_version_ 1719325475072901120