%0 Conference Proceedings
%T Divide-and-Learn: A Random Indexing Approach to Attribute Inference Attacks in Online Social Networks
%+ Università degli Studi di Roma "La Sapienza" = Sapienza University [Rome] (UNIROMA)
%+ Proof techniques for security protocols (PESTO)
%A Eidizadehakhcheloo, Sanaz
%A Pijani, Bizhan, Alipour
%A Imine, Abdessamad
%A Rusinowitch, Michaël
%Z Part 6: Potpourri II
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 35th IFIP Annual Conference on Data and Applications Security and Privacy (DBSec)
%C Calgary, AB, Canada
%I Springer International Publishing
%3 Data and Applications Security and Privacy XXXV
%V LNCS-12840
%P 338-356
%8 2021-07-19
%D 2021
%R 10.1007/978-3-030-81242-3_20
%K Social Networks
%K Privacy
%K Attribute Inference Attack
%K Random Indexing
%Z Computer Science [cs]/Social and Information Networks [cs.SI]
%Z Computer Science [cs]/Cryptography and Security [cs.CR]Conference papers
%X We present a Divide-and-Learn machine learning methodology to investigate a new class of attribute inference attacks against Online Social Networks (OSN) users. Our methodology analyzes commenters' preferences related to some user publications (e.g., posts or pictures) to infer sensitive attributes of that user. For classification performance, we tune Random Indexing (RI) to compute several embeddings for textual units (e.g., word, emoji), each one depending on a specific attribute value. RI guarantees the comparability of the generated vectors for the different values. To validate the approach, we consider three Facebook attributes: gender, age category and relationship status, which are highly relevant for targeted advertising or privacy threatening applications. By using an XGBoost classifier, we show that we can infer Facebook users' attributes from commenters' reactions to their publications with AUC from 94% to 98%, depending on the traits.
%G English
%Z TC 11
%Z WG 11.3
%2 https://inria.hal.science/hal-03463902/document
%2 https://inria.hal.science/hal-03463902/file/main.pdf
%L hal-03463902
%U https://inria.hal.science/hal-03463902
%~ UNIV-RENNES1
%~ CNRS
%~ INRIA
%~ IRISA
%~ INRIA_TEST
%~ INRIA-LORRAINE
%~ LORIA2
%~ INRIA-NANCY-GRAND-EST
%~ TESTALAIN1
%~ IFIP-LNCS
%~ IFIP
%~ UNIV-LORRAINE
%~ INRIA2
%~ IFIP-TC
%~ IFIP-WG
%~ IFIP-TC11
%~ IFIP-WG11-3
%~ IFIP-DBSEC
%~ UR1-HAL
%~ LORIA
%~ LORIA-FM
%~ UR1-MATH-STIC
%~ UR1-UFR-ISTIC
%~ TEST-UR-CSS
%~ UNIV-RENNES
%~ INRIA-300009
%~ IMPACT-DIGITRUST
%~ TEST-HALCNRS
%~ UR1-MATH-NUM
%~ IFIP-LNCS-12840