Enhancing privacy awareness in online social networks: A knowledge-driven approach

Hence, in this talk, we show our theoretical framework to i) measure the privacy risk of the users and alert them whenever their privacy is compromised and ii) help the exposed users customize semi-automatically their privacy level by limiting the number of manual operations thanks to an active learning approach. Moreover, instead of using a separation-based policy for computing the privacy risk, we adopt a circle-based formulation of the privacy score. We show experimentally that our circle-based definition of privacy score better capture the real privacy leakage risk. Moreover, by investigating the relationship between the privacy measure and the privacy preferences of real Facebook users, we show that our framework may effectively support a safer andmore fruitful experience in social networking sites. Then, we present a new network-aware computational method for measuring the privacy risk, and report on a social experiment we performed, which involves more than one hundred Facebook users. Thanks to this experiment, we show the effectiveness of our privacy measure not only on two simulated networks but also on a large network of real Facebook users.