Misinformation in Third-party Voice Applications

Jide Edu; Jose Such; Guillermo Suarez-Tangil; Mary Bispham; Suliman  Kalim Sattar; Clara Zard

Misinformation in Third-party Voice Applications

Jide Edu, Jose Such, Guillermo Suarez-Tangil, Mary Bispham, Suliman Kalim Sattar, Clara Zard

King's College London (KCL)

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

75 Downloads (Pure)

Abstract

This paper investigates the potential for spreading misinformation via third-party voice applications in voice assistant ecosystems such as Amazon Alexa and Google Assistant. Our work fills a gap in prior work on privacy issues associated with third-party voice applications, looking at security issues related to outputs from such applications rather than compromises to privacy from user inputs.
We define misinformation in the context of third-party voice applications and implement an infrastructure for testing third-party voice applications using automated natural language interaction. Using our infrastructure, we identify --- for the first time --- several instances of misinformation in third-party voice applications currently available on the Google Assistant and Amazon Alexa platforms. We then discuss the implications of our work for developing measures to pre-empt the threat of misinformation and other types of harmful content in third-party voice assistants becoming more significant in the future.

Original language	English
Title of host publication	Special Interest Group on Computer-Human Interaction
Publisher	ACM
Number of pages	6
Publication status	Accepted/In press - 28 May 2023
Event	ACM conference on Conversational User Interfaces - Eindhoven, Netherlands Duration: 19 Jul 2023 → 21 Jul 2023 Conference number: 23

Conference

Conference	ACM conference on Conversational User Interfaces
Abbreviated title	CUI
Country/Territory	Netherlands
City	Eindhoven
Period	19/07/2023 → 21/07/2023

Access to Document

CUI___SkillInterrogator_misinformation_paper

Cite this

@inbook{e72d095c2821415c9fe3ce048cc0a5f5,

title = "Misinformation in Third-party Voice Applications",

abstract = "This paper investigates the potential for spreading misinformation via third-party voice applications in voice assistant ecosystems such as Amazon Alexa and Google Assistant. Our work fills a gap in prior work on privacy issues associated with third-party voice applications, looking at security issues related to outputs from such applications rather than compromises to privacy from user inputs.We define misinformation in the context of third-party voice applications and implement an infrastructure for testing third-party voice applications using automated natural language interaction. Using our infrastructure, we identify --- for the first time --- several instances of misinformation in third-party voice applications currently available on the Google Assistant and Amazon Alexa platforms. We then discuss the implications of our work for developing measures to pre-empt the threat of misinformation and other types of harmful content in third-party voice assistants becoming more significant in the future.",

author = "Jide Edu and Jose Such and Guillermo Suarez-Tangil and Mary Bispham and {Kalim Sattar}, Suliman and Clara Zard",

year = "2023",

month = may,

day = "28",

language = "English",

booktitle = "Special Interest Group on Computer-Human Interaction",

publisher = "ACM",

note = "ACM conference on Conversational User Interfaces, CUI ; Conference date: 19-07-2023 Through 21-07-2023",

}

TY - CHAP

T1 - Misinformation in Third-party Voice Applications

AU - Edu, Jide

AU - Such, Jose

AU - Suarez-Tangil, Guillermo

AU - Bispham, Mary

AU - Kalim Sattar, Suliman

AU - Zard, Clara

N1 - Conference code: 23

PY - 2023/5/28

Y1 - 2023/5/28

N2 - This paper investigates the potential for spreading misinformation via third-party voice applications in voice assistant ecosystems such as Amazon Alexa and Google Assistant. Our work fills a gap in prior work on privacy issues associated with third-party voice applications, looking at security issues related to outputs from such applications rather than compromises to privacy from user inputs.We define misinformation in the context of third-party voice applications and implement an infrastructure for testing third-party voice applications using automated natural language interaction. Using our infrastructure, we identify --- for the first time --- several instances of misinformation in third-party voice applications currently available on the Google Assistant and Amazon Alexa platforms. We then discuss the implications of our work for developing measures to pre-empt the threat of misinformation and other types of harmful content in third-party voice assistants becoming more significant in the future.

AB - This paper investigates the potential for spreading misinformation via third-party voice applications in voice assistant ecosystems such as Amazon Alexa and Google Assistant. Our work fills a gap in prior work on privacy issues associated with third-party voice applications, looking at security issues related to outputs from such applications rather than compromises to privacy from user inputs.We define misinformation in the context of third-party voice applications and implement an infrastructure for testing third-party voice applications using automated natural language interaction. Using our infrastructure, we identify --- for the first time --- several instances of misinformation in third-party voice applications currently available on the Google Assistant and Amazon Alexa platforms. We then discuss the implications of our work for developing measures to pre-empt the threat of misinformation and other types of harmful content in third-party voice assistants becoming more significant in the future.

M3 - Conference paper

BT - Special Interest Group on Computer-Human Interaction

PB - ACM

T2 - ACM conference on Conversational User Interfaces

Y2 - 19 July 2023 through 21 July 2023

ER -

Misinformation in Third-party Voice Applications

Abstract

Conference

Access to Document

Fingerprint

Cite this