Online Testing of User Profile Resilience Against Inference Attacks in Social Networks

Younes Abid 1 Abdessamad Imine 1 Michael Rusinowitch 1
1 PESTO - Proof techniques for security protocols
Inria Nancy - Grand Est, LORIA - FM - Department of Formal Methods
Abstract : To increase awareness about privacy threats, we have designed a tool, SONSAI, for Facebook users to audit their own profiles. SONSAI predicts values of sensitive attributes by machine learning and identifies user public attributes that have guided the learning algorithm towards these sensitive attribute values. Here, we present new aspects of the system such as the automatic combination of link disclosure attacks and attribute prediction. We explain how we defined sensitive subjects from a survey. We also show how the extended tool is fully interfaced with Facebook along different scenarios. In each case a dataset was built from real profiles collected in the user neighbourhood network. The whole analysis process is performed online, mostly automatically and with accuracy of 0.79 in AUC when inferring the political orientation.
Document type :
Conference papers
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download
Contributor : Abdessamad Imine <>
Submitted on : Wednesday, December 12, 2018 - 9:10:22 AM
Last modification on : Tuesday, December 18, 2018 - 4:38:25 PM
Long-term archiving on : Wednesday, March 13, 2019 - 12:44:37 PM


Files produced by the author(s)


  • HAL Id : hal-01939277, version 1



Younes Abid, Abdessamad Imine, Michael Rusinowitch. Online Testing of User Profile Resilience Against Inference Attacks in Social Networks. ADBIS 2018 - First International Workshop on Advances on Big Data Management, Analytics, Data Privacy and Security, BigDataMAPS 2018, Sep 2018, Budapest, Hungary. ⟨hal-01939277⟩



Record views


Files downloads