Section: New Results

Online Social Networks

Social media such as Facebook provides a new way to connect, interact and learn. Facebook allows users to share photos and express their feelings by using comments. However, Facebook users are vulnerable to attribute inference attacks where an attacker intends to guess private attributes (e.g., gender, age, political view) of target users through their online profiles and/or their vicinity (e.g., what their friends reveal). Given user-generated pictures on Facebook, we show in [16] how to launch gender inference attacks on their owners from pictures meta-data composed of: (i) alt-texts generated by Facebook to describe the content of pictures, and (ii) comments posted by friends, friends of friends or regular users. We assume these two meta-data are the only available information to the attacker. Evaluation results demonstrate that our attack technique can infer the gender with an accuracy of $84\%$ by leveraging only alt-texts, $96\%$ by using only comments, and $98\%$ by combining alt-texts and comments. We compute a set of sensitive words that enable attackers to perform effective gender inference attacks. We show the adversary prediction accuracy is decreased by hiding these sensitive words. To the best of our knowledge, this is the first inference attack on Facebook that exploits comments and alt-texts solely. In subsequent work we have investigated the case where comments are reduced to Emojis.

In a joint project with the Resist research group at Inria Nancy and Numeryx company, we are working on the design, implementation and evaluation of a double-mask technique for building compressed and verifiable filtering rules in Software Defined Networks with the possibility of distributing the workload processing among several packet filtering devices operating in parallel [33], [34].