Hiding individuals and communities in a social network

Marcin Waniek, Tomasz P. Michalak, Michael J. Wooldridge, Talal Rahwan

Research output: Contribution to journalArticle

Abstract

The Internet and social media have fuelled enormous interest in social network analysis. New tools continue to be developed and used to analyse our personal connections, with particular emphasis on detecting communities or identifying key individuals in a social network. This raises privacy concerns that are likely to exacerbate in the future. With this in mind, we ask the question 'Can individuals or groups actively manage their connections to evade social network analysis tools?' By addressing this question, the general public may better protect their privacy, oppressed activist groups may better conceal their existence and security agencies may better understand how terrorists escape detection. We first study how an individual can evade 'node centrality' analysis while minimizing the negative impact that this may have on his or her influence. We prove that an optimal solution to this problem is difficult to compute. Despite this hardness, we demonstrate how even a simple heuristic, whereby attention is restricted to the individual's immediate neighbourhood, can be surprisingly effective in practice; for example, it could easily disguise Mohamed Atta's leading position within the World Trade Center terrorist network. We also study how a community can increase the likelihood of being overlooked by community-detection algorithms. We propose a measure of concealment-expressing how well a community is hidden-and use it to demonstrate the effectiveness of a simple heuristic, whereby members of the community either 'unfriend' certain other members or 'befriend' some non-members in a coordinated effort to camouflage their community.

Original languageEnglish (US)
Pages (from-to)139-147
Number of pages9
JournalNature Human Behaviour
Volume2
Issue number2
DOIs
StatePublished - Feb 1 2018

Fingerprint

Social Support
Privacy
Social Media
Hardness
Internet

ASJC Scopus subject areas

  • Social Psychology
  • Experimental and Cognitive Psychology
  • Behavioral Neuroscience

Cite this

Hiding individuals and communities in a social network. / Waniek, Marcin; Michalak, Tomasz P.; Wooldridge, Michael J.; Rahwan, Talal.

In: Nature Human Behaviour, Vol. 2, No. 2, 01.02.2018, p. 139-147.

Research output: Contribution to journalArticle

Waniek, Marcin ; Michalak, Tomasz P. ; Wooldridge, Michael J. ; Rahwan, Talal. / Hiding individuals and communities in a social network. In: Nature Human Behaviour. 2018 ; Vol. 2, No. 2. pp. 139-147.
@article{7fb485e7b6c442c79ede29f60c5e920e,
title = "Hiding individuals and communities in a social network",
abstract = "The Internet and social media have fuelled enormous interest in social network analysis. New tools continue to be developed and used to analyse our personal connections, with particular emphasis on detecting communities or identifying key individuals in a social network. This raises privacy concerns that are likely to exacerbate in the future. With this in mind, we ask the question 'Can individuals or groups actively manage their connections to evade social network analysis tools?' By addressing this question, the general public may better protect their privacy, oppressed activist groups may better conceal their existence and security agencies may better understand how terrorists escape detection. We first study how an individual can evade 'node centrality' analysis while minimizing the negative impact that this may have on his or her influence. We prove that an optimal solution to this problem is difficult to compute. Despite this hardness, we demonstrate how even a simple heuristic, whereby attention is restricted to the individual's immediate neighbourhood, can be surprisingly effective in practice; for example, it could easily disguise Mohamed Atta's leading position within the World Trade Center terrorist network. We also study how a community can increase the likelihood of being overlooked by community-detection algorithms. We propose a measure of concealment-expressing how well a community is hidden-and use it to demonstrate the effectiveness of a simple heuristic, whereby members of the community either 'unfriend' certain other members or 'befriend' some non-members in a coordinated effort to camouflage their community.",
author = "Marcin Waniek and Michalak, {Tomasz P.} and Wooldridge, {Michael J.} and Talal Rahwan",
year = "2018",
month = "2",
day = "1",
doi = "10.1038/s41562-017-0290-3",
language = "English (US)",
volume = "2",
pages = "139--147",
journal = "Nature Human Behaviour",
issn = "2397-3374",
publisher = "Nature Publishing Group",
number = "2",

}

TY - JOUR

T1 - Hiding individuals and communities in a social network

AU - Waniek, Marcin

AU - Michalak, Tomasz P.

AU - Wooldridge, Michael J.

AU - Rahwan, Talal

PY - 2018/2/1

Y1 - 2018/2/1

N2 - The Internet and social media have fuelled enormous interest in social network analysis. New tools continue to be developed and used to analyse our personal connections, with particular emphasis on detecting communities or identifying key individuals in a social network. This raises privacy concerns that are likely to exacerbate in the future. With this in mind, we ask the question 'Can individuals or groups actively manage their connections to evade social network analysis tools?' By addressing this question, the general public may better protect their privacy, oppressed activist groups may better conceal their existence and security agencies may better understand how terrorists escape detection. We first study how an individual can evade 'node centrality' analysis while minimizing the negative impact that this may have on his or her influence. We prove that an optimal solution to this problem is difficult to compute. Despite this hardness, we demonstrate how even a simple heuristic, whereby attention is restricted to the individual's immediate neighbourhood, can be surprisingly effective in practice; for example, it could easily disguise Mohamed Atta's leading position within the World Trade Center terrorist network. We also study how a community can increase the likelihood of being overlooked by community-detection algorithms. We propose a measure of concealment-expressing how well a community is hidden-and use it to demonstrate the effectiveness of a simple heuristic, whereby members of the community either 'unfriend' certain other members or 'befriend' some non-members in a coordinated effort to camouflage their community.

AB - The Internet and social media have fuelled enormous interest in social network analysis. New tools continue to be developed and used to analyse our personal connections, with particular emphasis on detecting communities or identifying key individuals in a social network. This raises privacy concerns that are likely to exacerbate in the future. With this in mind, we ask the question 'Can individuals or groups actively manage their connections to evade social network analysis tools?' By addressing this question, the general public may better protect their privacy, oppressed activist groups may better conceal their existence and security agencies may better understand how terrorists escape detection. We first study how an individual can evade 'node centrality' analysis while minimizing the negative impact that this may have on his or her influence. We prove that an optimal solution to this problem is difficult to compute. Despite this hardness, we demonstrate how even a simple heuristic, whereby attention is restricted to the individual's immediate neighbourhood, can be surprisingly effective in practice; for example, it could easily disguise Mohamed Atta's leading position within the World Trade Center terrorist network. We also study how a community can increase the likelihood of being overlooked by community-detection algorithms. We propose a measure of concealment-expressing how well a community is hidden-and use it to demonstrate the effectiveness of a simple heuristic, whereby members of the community either 'unfriend' certain other members or 'befriend' some non-members in a coordinated effort to camouflage their community.

UR - http://www.scopus.com/inward/record.url?scp=85042772086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042772086&partnerID=8YFLogxK

U2 - 10.1038/s41562-017-0290-3

DO - 10.1038/s41562-017-0290-3

M3 - Article

AN - SCOPUS:85042772086

VL - 2

SP - 139

EP - 147

JO - Nature Human Behaviour

JF - Nature Human Behaviour

SN - 2397-3374

IS - 2

ER -