HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation

Attribute inference attacks on social media publications

Bizhan Alipour Pijani 1
1 PESTO - Proof techniques for security protocols
Inria Nancy - Grand Est, LORIA - FM - Department of Formal Methods
Abstract : Online Social Networks (OSN) are full of personal information such as gender, age, relationship status. The popularity and growth of OSN have rendered their platforms vulnerable to malicious activities and increased user privacy concerns. The privacy settings available in OSN do not prevent users from attribute inference attacks where an attacker seeks to illegitimately obtain their personal attributes (such as the gender attribute) from publicly available information. Disclosure of personal information can have serious outcomes such as personal spam, bullying, profile cloning for malicious activities, or sexual harassment. Existing inference techniques are either based on the target user behavior analysis through their liked pages and group memberships or based on the target user friend list. However, in real cases, the amount of available information to an attacker is small since users have realized the vulnerability of standard attribute inference attacks and concealed their generated information. To increase awareness of OSN users about threats to their privacy, in this thesis, we introduce a new class of attribute inference attacks against OSN users. We show the feasibility of these attacks from a very limited amount of data. They are applicable even when users hide all their profile information and their own comments. Our proposed methodology is to analyze Facebook picture metadata, namely (i) alt-text generated by Facebook to describe picture contents, and (ii) commenters’ words and emojis preferences while commenting underneath the picture, to infer sensitive attributes of the picture owner. We show how to launch these inference attacks on any Facebook user by i) handling online newly discovered vocabulary using a retrofitting process to enrich a core vocabulary that was built during offline training and ii) computing several embeddings for textual units (e.g., word, emoji), each one depending on a specific attribute value. Finally, we introduce ProPic, a protection mechanism that selects comments to be hidden in a computationally efficient way while minimizing utility loss according to a semantic measure. The proposed mechanism can help end-users to check their vulnerability to inference attacks and suggests comments to be hidden in order to mitigate the attacks. We have determined the success of the attacks and the protection mechanism by experiments on real data.
Complete list of metadata

Contributor : Thèses Ul Connect in order to contact the contributor
Submitted on : Thursday, May 12, 2022 - 3:36:46 PM
Last modification on : Friday, May 13, 2022 - 3:36:51 AM


Files produced by the author(s)


  • HAL Id : tel-03666575, version 1


Bizhan Alipour Pijani. Attribute inference attacks on social media publications. Computer Science [cs]. Université de Lorraine, 2022. English. ⟨NNT : 2022LORR0009⟩. ⟨tel-03666575⟩



Record views


Files downloads