Thwarting fake OSN accounts by predicting their victims

Yazan Boshmaf, Matei Ripeanu, Konstantin Beznosov, Elizeu Santos-Neto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Traditional defense mechanisms for fighting against automated fake accounts in online social networks are victim-agnostic. Even though victims of fake accounts play an important role in the viability of subsequent attacks, there is no work on utilizing this insight to improve the status quo. In this position paper, we take the first step and propose to incorporate predictions about victims of unknown fakes into the workflows of existing defense mechanisms. In particular, we investigated how such an integration could lead to more robust fake account defense mechanisms. We also used real-world datasets from Facebook and Tuenti to evaluate the feasibility of predicting victims of fake accounts using supervised machine learning.

Original languageEnglish
Title of host publicationAISec 2015 - Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2015
PublisherAssociation for Computing Machinery, Inc
Pages81-90
Number of pages10
ISBN (Electronic)9781450338264
DOIs
Publication statusPublished - 16 Oct 2015
Externally publishedYes
Event8th ACM Workshop on Artificial Intelligence and Security, AISec 2015 - co-located with CCS 2015 - Denver, United States
Duration: 16 Oct 2015 → …

Other

Other8th ACM Workshop on Artificial Intelligence and Security, AISec 2015 - co-located with CCS 2015
CountryUnited States
CityDenver
Period16/10/15 → …

Fingerprint

Learning systems

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Boshmaf, Y., Ripeanu, M., Beznosov, K., & Santos-Neto, E. (2015). Thwarting fake OSN accounts by predicting their victims. In AISec 2015 - Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2015 (pp. 81-90). Association for Computing Machinery, Inc. https://doi.org/10.1145/2808769.2808772

Thwarting fake OSN accounts by predicting their victims. / Boshmaf, Yazan; Ripeanu, Matei; Beznosov, Konstantin; Santos-Neto, Elizeu.

AISec 2015 - Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2015. Association for Computing Machinery, Inc, 2015. p. 81-90.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Boshmaf, Y, Ripeanu, M, Beznosov, K & Santos-Neto, E 2015, Thwarting fake OSN accounts by predicting their victims. in AISec 2015 - Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2015. Association for Computing Machinery, Inc, pp. 81-90, 8th ACM Workshop on Artificial Intelligence and Security, AISec 2015 - co-located with CCS 2015, Denver, United States, 16/10/15. https://doi.org/10.1145/2808769.2808772
Boshmaf Y, Ripeanu M, Beznosov K, Santos-Neto E. Thwarting fake OSN accounts by predicting their victims. In AISec 2015 - Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2015. Association for Computing Machinery, Inc. 2015. p. 81-90 https://doi.org/10.1145/2808769.2808772
Boshmaf, Yazan ; Ripeanu, Matei ; Beznosov, Konstantin ; Santos-Neto, Elizeu. / Thwarting fake OSN accounts by predicting their victims. AISec 2015 - Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2015. Association for Computing Machinery, Inc, 2015. pp. 81-90
@inproceedings{992e8a3e244b4afd9498fb92a0e48c4a,
title = "Thwarting fake OSN accounts by predicting their victims",
abstract = "Traditional defense mechanisms for fighting against automated fake accounts in online social networks are victim-agnostic. Even though victims of fake accounts play an important role in the viability of subsequent attacks, there is no work on utilizing this insight to improve the status quo. In this position paper, we take the first step and propose to incorporate predictions about victims of unknown fakes into the workflows of existing defense mechanisms. In particular, we investigated how such an integration could lead to more robust fake account defense mechanisms. We also used real-world datasets from Facebook and Tuenti to evaluate the feasibility of predicting victims of fake accounts using supervised machine learning.",
author = "Yazan Boshmaf and Matei Ripeanu and Konstantin Beznosov and Elizeu Santos-Neto",
year = "2015",
month = "10",
day = "16",
doi = "10.1145/2808769.2808772",
language = "English",
pages = "81--90",
booktitle = "AISec 2015 - Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2015",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Thwarting fake OSN accounts by predicting their victims

AU - Boshmaf, Yazan

AU - Ripeanu, Matei

AU - Beznosov, Konstantin

AU - Santos-Neto, Elizeu

PY - 2015/10/16

Y1 - 2015/10/16

N2 - Traditional defense mechanisms for fighting against automated fake accounts in online social networks are victim-agnostic. Even though victims of fake accounts play an important role in the viability of subsequent attacks, there is no work on utilizing this insight to improve the status quo. In this position paper, we take the first step and propose to incorporate predictions about victims of unknown fakes into the workflows of existing defense mechanisms. In particular, we investigated how such an integration could lead to more robust fake account defense mechanisms. We also used real-world datasets from Facebook and Tuenti to evaluate the feasibility of predicting victims of fake accounts using supervised machine learning.

AB - Traditional defense mechanisms for fighting against automated fake accounts in online social networks are victim-agnostic. Even though victims of fake accounts play an important role in the viability of subsequent attacks, there is no work on utilizing this insight to improve the status quo. In this position paper, we take the first step and propose to incorporate predictions about victims of unknown fakes into the workflows of existing defense mechanisms. In particular, we investigated how such an integration could lead to more robust fake account defense mechanisms. We also used real-world datasets from Facebook and Tuenti to evaluate the feasibility of predicting victims of fake accounts using supervised machine learning.

UR - http://www.scopus.com/inward/record.url?scp=84960511002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960511002&partnerID=8YFLogxK

U2 - 10.1145/2808769.2808772

DO - 10.1145/2808769.2808772

M3 - Conference contribution

SP - 81

EP - 90

BT - AISec 2015 - Proceedings of the 8th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2015

PB - Association for Computing Machinery, Inc

ER -