Machine Learning Voice Synthesis for Intention Electromagnetic Interference Injection in Smart Speaker Devices

Abstract

This work presents the effectiveness of using machine learning (ML) synthesized voice samples to control smart speaker devices through radiated intentional electromagnetic interference (I-EMI). In previous works, the feasibility of using I-EMI to control smart speaker devices was shown. However, 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 this attack. By training a generative adversarial network (GAN) using samples of the target's voice, this security feature can be bypassed directly, increasing the feasibility of the attack.

Meeting Name

2021 IEEE International Joint Electromagnetic Compatibility Signal and Power Integrity and EMC Europe Symposium, EMC/SI/PI/EMC Europe 2021 (2021: Jul. 26-Aug. 13, Raleigh, NC)

Department(s)

Electrical and Computer Engineering

Research Center/Lab(s)

Electromagnetic Compatibility (EMC) Laboratory

Comments

This work was supported in part by the National Science Foundation (NSF) under Grant IIP-1916535.

Keywords and Phrases

Electromagnetic Interference (EMI); Generative Adversarial Networks (GAN); Internet of Things (IoT); Machine Learning (ML)

International Standard Book Number (ISBN)

978-166544888-8

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2021 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

13 Aug 2021

Link to Full Text

Share

 
COinS