Masters Theses

Keywords and Phrases

Hardware Security; Intentional Electromagnetic Interference; IoT; Smart Speakers


"Smart home and Internet of Things (IoT) devices have become ubiquitous in homes over the past decade. The smart speaker itself is often the device that interfaces all these devices together. Because of this, the smart speaker can become a point of attack for someone trying to exploit or hack into the smart home devices. In the past few years, it was discovered that smart speakers with microwave electromechanical system (MEMS) microphones are susceptible to intentional electromagnetic interference (I-EMI) attacks by modulating an audio command to a high-frequency carrier signal. This attack allows for command recognition for long-distances and smart speakers behind walls.

First, a method for modeling and understanding the smart speaker I-EMI attack is shown. This includes a method for finding the ideal attack angle, locating the region sensitive to the coupled EMI, and modeling the attack. Finally, using all these methods, a long distance (6-meter) attack is demonstrated using 6.3 Watts of power at the aggressor antenna.

Next, the effectiveness of using machine learning (ML) synthesized voice samples to control smart speaker devices through radiated intentional electromagnetic interference (I-EMI) in presented. Devices that are trained to only recognize a single person’s voice or only execute certain commands from that person will not be as susceptible to the I-EMI attack. By training a neural network using samples of the target’s voice, this security feature can be bypassed, increasing the feasibility of the attack"--Abstract, p. iv


Hwang, Chulsoon

Committee Member(s)

Kim, DongHyun (Bill)
Beetner, Daryl G.


Electrical and Computer Engineering

Degree Name

M.S. in Electrical and Computer Engineering


Missouri University of Science and Technology

Publication Date

Spring 2023


ix, 48 pages

Note about bibliography

Includes_bibliographical_references_(pages 45-46)


© 2023 Tanner Fokkens, All Rights Reserved

Document Type

Thesis - Open Access

File Type




Thesis Number

T 12244

Electronic OCLC #