Privacy protection of online social network users, against attribute inference attacks, through the use of a set of exhaustive rules

Abstract

A malicious data-miner can infer users' private information in online social networks (OSNs) by data mining the users' disclosed information. By exploring the public information about a target user (i.e. an individual or a group of OSN users whose privacy is under attack), attackers can prepare a training data set holding similar information about other users who openly disclosed their data. Using a machine learning classifier, the attacker can input released information about users under attack as non-class attributes and extract the private information as a class attribute. Some techniques offer some privacy protection against specific classifiers, however, the provided privacy can be under threat if an attacker uses a different classifier (rather than the one used by the privacy protection techniques) to infer sensitive information. In reality, it is difficult to predict the classifiers involved in a privacy attack. In this study, we propose a privacy-preserving technique which first prepares a training data set in a similar way that an attacker can prepare and then takes an approach independent of the classifiers to extract patterns (or logic rules) from the training data set. Based on the extracted rule set, it then suggests

An Automatic Privacy-Aware Framework for Text Data in Online Social Network Based on a Multi-Deep Learning Model

“…Te frst direction is privacy information measurement in social networks [37,38], while the second one is privacy protection in social networks [39]. In social network privacy information measurement, Buchanan et al used a questionnaire to compute the privacy scale of multiple dimensions; a reliable and efective social network privacy measurement was eventually obtained by verifying the validity of diferential data [40].…”

A Multiple Salient Features-Based User Identification across Social Media

“…Xing et al [6] proposed the use of multi-dimensional user attribute information for user identification, which involved 17 user attributes and achieved a better identification effect. However, from the perspective of user privacy protection [26], this work is susceptible to the limitations of the lack of user profile information. Moreover, the forgery of user attribute information has a greater impact on the final result of user identification.…”

“…Although a small amount of user information is used to achieve better multi-user identification, it also provides a shortcut for some malicious attackers in the network to obtain normal user information [26]. Therefore, future work should consider from the perspective of game theory to balance the relationship between user information and privacy protection.…”

Application of Personal Information Privacy Protection Based on Machine Learning Algorithm

“…Research on key technologies of data privacy protection under the mode [ 12 ]. Reza et al [ 13 ] took the hybrid cloud as the data bearing platform, proposed a data segmentation technology based on the k-anonymity criterion, and designed a complete set of data anonymity segmentation scheme to solve the balance of data privacy protection and availability when the set-valued data is released [ 13 ]. Wei et al [ 14 ] believe that attackers can obtain data privacy by filtering random noise.…”