Security risks of social robots used to persuade and manipulate: a proof of concept study

Pieter Wolfert; Jorre Deschuyteneer; Djamari  Oetringer; Nicole Robinson; Tony Belpaeme

doi:10.1145/3371382.3378341

Security risks of social robots used to persuade and manipulate: a proof of concept study

Pieter Wolfert, Jorre Deschuyteneer, Djamari Oetringer, Nicole Robinson, Tony Belpaeme

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

Abstract

Earlier research has shown that robots can provoke social responses in people, and that robots often elicit compliance. In this paper we discuss three proof of concept studies in which we explore the possibility of robots being hacked and taken over by others with the explicit purpose of using the robot’s social capabilities. Three scenarios are explored: gaining access to secured areas, extracting sensitive and personal information, and convincing people to take unsafe action. We find that people are willing to do these tasks, and that social robots tend to be trusted, even in situations that would normally cause suspicion.

Original language	English
Title of host publication	Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction
Editors	Hatice Gunes, Laurel Riek
Place of Publication	New York NY USA
Publisher	Association for Computing Machinery (ACM)
Pages	523-525
Number of pages	3
ISBN (Print)	9781450370578
DOIs	https://doi.org/10.1145/3371382.3378341
Publication status	Published - Mar 2020
Externally published	Yes
Event	Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2020 - Cambridge, United Kingdom Duration: 23 Mar 2020 → 26 Mar 2020 Conference number: 15th http://humanrobotinteraction.org/2020/ https://dl.acm.org/doi/proceedings/10.1145/3319502 (Proceedings)

Conference

Conference	Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2020
Abbreviated title	HRI 2020
Country/Territory	United Kingdom
City	Cambridge
Period	23/03/20 → 26/03/20
Internet address	http://humanrobotinteraction.org/2020/ https://dl.acm.org/doi/proceedings/10.1145/3319502 (Proceedings)

Access to Document

10.1145/3371382.3378341

301563737-oaFinal published version, 5.04 MB

Cite this

Wolfert, P., Deschuyteneer, J., Oetringer, D., Robinson, N., & Belpaeme, T. (2020). Security risks of social robots used to persuade and manipulate: a proof of concept study. In H. Gunes, & L. Riek (Eds.), Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction (pp. 523-525). Association for Computing Machinery (ACM). https://doi.org/10.1145/3371382.3378341

Wolfert, Pieter ; Deschuyteneer, Jorre ; Oetringer, Djamari ; Robinson, Nicole ; Belpaeme, Tony. / Security risks of social robots used to persuade and manipulate : a proof of concept study. Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction. editor / Hatice Gunes ; Laurel Riek. New York NY USA : Association for Computing Machinery (ACM), 2020. pp. 523-525

@inproceedings{32a4268e1e1d4e4c987c950b503a5a8f,

title = "Security risks of social robots used to persuade and manipulate: a proof of concept study",

abstract = "Earlier research has shown that robots can provoke social responses in people, and that robots often elicit compliance. In this paper we discuss three proof of concept studies in which we explore the possibility of robots being hacked and taken over by others with the explicit purpose of using the robot{\textquoteright}s social capabilities. Three scenarios are explored: gaining access to secured areas, extracting sensitive and personal information, and convincing people to take unsafe action. We find that people are willing to do these tasks, and that social robots tend to be trusted, even in situations that would normally cause suspicion.",

author = "Pieter Wolfert and Jorre Deschuyteneer and Djamari Oetringer and Nicole Robinson and Tony Belpaeme",

year = "2020",

month = mar,

doi = "10.1145/3371382.3378341",

language = "English",

isbn = "9781450370578",

pages = "523--525",

editor = "Hatice Gunes and Laurel Riek",

booktitle = "Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

note = "Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2020, HRI 2020 ; Conference date: 23-03-2020 Through 26-03-2020",

url = "http://humanrobotinteraction.org/2020/, https://dl.acm.org/doi/proceedings/10.1145/3319502",

}

Wolfert, P, Deschuyteneer, J, Oetringer, D, Robinson, N & Belpaeme, T 2020, Security risks of social robots used to persuade and manipulate: a proof of concept study. in H Gunes & L Riek (eds), Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction. Association for Computing Machinery (ACM), New York NY USA, pp. 523-525, Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2020, Cambridge, United Kingdom, 23/03/20. https://doi.org/10.1145/3371382.3378341

Security risks of social robots used to persuade and manipulate : a proof of concept study. / Wolfert, Pieter; Deschuyteneer, Jorre; Oetringer, Djamari; Robinson, Nicole; Belpaeme, Tony.

Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction. ed. / Hatice Gunes; Laurel Riek. New York NY USA : Association for Computing Machinery (ACM), 2020. p. 523-525.

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

TY - GEN

T1 - Security risks of social robots used to persuade and manipulate

T2 - Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2020

AU - Wolfert, Pieter

AU - Deschuyteneer, Jorre

AU - Oetringer, Djamari

AU - Robinson, Nicole

AU - Belpaeme, Tony

N1 - Conference code: 15th

PY - 2020/3

Y1 - 2020/3

N2 - Earlier research has shown that robots can provoke social responses in people, and that robots often elicit compliance. In this paper we discuss three proof of concept studies in which we explore the possibility of robots being hacked and taken over by others with the explicit purpose of using the robot’s social capabilities. Three scenarios are explored: gaining access to secured areas, extracting sensitive and personal information, and convincing people to take unsafe action. We find that people are willing to do these tasks, and that social robots tend to be trusted, even in situations that would normally cause suspicion.

AB - Earlier research has shown that robots can provoke social responses in people, and that robots often elicit compliance. In this paper we discuss three proof of concept studies in which we explore the possibility of robots being hacked and taken over by others with the explicit purpose of using the robot’s social capabilities. Three scenarios are explored: gaining access to secured areas, extracting sensitive and personal information, and convincing people to take unsafe action. We find that people are willing to do these tasks, and that social robots tend to be trusted, even in situations that would normally cause suspicion.

U2 - 10.1145/3371382.3378341

DO - 10.1145/3371382.3378341

M3 - Conference Paper

SN - 9781450370578

SP - 523

EP - 525

BT - Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction

A2 - Gunes, Hatice

A2 - Riek, Laurel

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

Y2 - 23 March 2020 through 26 March 2020

ER -

Wolfert P, Deschuyteneer J, Oetringer D, Robinson N, Belpaeme T. Security risks of social robots used to persuade and manipulate: a proof of concept study. In Gunes H, Riek L, editors, Companion of the 2020 ACM/IEEE International Conference on Human-Robot Interaction. New York NY USA: Association for Computing Machinery (ACM). 2020. p. 523-525 https://doi.org/10.1145/3371382.3378341