Protection of user-defined sensitive attributes on online social networks against attribute inference attack via adversarial data mining

Jahid Reza, Md Zahidul Islam, Vladimir Estivill-Castro

Research output: Book chapter/Published conference paperConference paper

Abstract

Online social network (OSN) users share various types of personal information with other users. By analysing such personal information, a malicious data miner (or an attacker) can infer the sensitive information about the user which has not been disclosed publicly. This is generally known as attribute inference attack. In this study, we propose a privacy preserving technique, namely 3LP+, that can protect users’ multiple sensitive information from being inferred. We experimentally show that the 3LP+ algorithm can provide better privacy than an existing technique while maintaining the utility of users’ data.

Original languageEnglish
Title of host publicationInformation Systems Security and Privacy - 5th International Conference, ICISSP 2019, Revised Selected Papers
EditorsPaolo Mori, Steven Furnell, Olivier Camp
PublisherSpringer
Pages230-249
Number of pages20
ISBN (Print)9783030494421
DOIs
Publication statusE-pub ahead of print - 28 Jun 2020
Event5th International Conference on Information Systems Security and Privacy: ICISSP 2019 - Vienna House Diplomat Prague, Prague, Czech Republic
Duration: 23 Feb 201925 Feb 2019
http://www.icissp.org/?y=2019 (Conference website)
https://www.scitepress.org/ProceedingsDetails.aspx?ID=2JXfLZNuB94=&t=1 (proceedings)
http://www.icissp.org/CallForPapers.aspx?y=2019 (call for papers)
https://www.springer.com/gp/book/9783030494421 (proceedings)

Publication series

NameCommunications in Computer and Information Science
Volume1221 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference5th International Conference on Information Systems Security and Privacy
CountryCzech Republic
CityPrague
Period23/02/1925/02/19
OtherThe International Conference on Information Systems Security and Privacy aims at creating a meeting point for researchers and practitioners that address security and privacy challenges that concern information systems, especially in organizations, including not only technological issues but also social issues. The conference welcomes papers of either practical or theoretical nature, presenting research or applications addressing all aspects of security and privacy, that concerns to organizations and individuals, thus creating new research opportunities.
Internet address

Fingerprint Dive into the research topics of 'Protection of user-defined sensitive attributes on online social networks against attribute inference attack via adversarial data mining'. Together they form a unique fingerprint.

  • Cite this

    Reza, J., Islam, M. Z., & Estivill-Castro, V. (2020). Protection of user-defined sensitive attributes on online social networks against attribute inference attack via adversarial data mining. In P. Mori, S. Furnell, & O. Camp (Eds.), Information Systems Security and Privacy - 5th International Conference, ICISSP 2019, Revised Selected Papers (pp. 230-249). (Communications in Computer and Information Science; Vol. 1221 CCIS). Springer. https://doi.org/10.1007/978-3-030-49443-8_11