Enforcing transparent access to private content in social networks by means of automatic sanitization

Abstract

Social networks have become an essential meeting point for millions of individuals willing to publish and consume huge quantities of heterogeneous information. Some studies have shown that the data published in these platforms may contain sensitive personal information and that external entities can gather and exploit this knowledge for their own benefit. Even though some methods to preserve the privacy of social networks users have been proposed, they generally apply rigid access control measures to the protected content and, even worse, they do not enable the users to understand which contents are sensitive. Last but not least, most of them require the collaboration of social network operators or they fail to provide a practical solution capable of working with well-known and already deployed social platforms. In this paper, we propose a new scheme that addresses all these issues. The new system is envisaged as an independent piece of software that does not depend on the social network in use and that can be transparently applied to most existing ones. According to a set of privacy requirements intuitively defined by the users of a social network, the proposed scheme is able to: (i) automatically detect sensitive data in users' publications; (ii) construct sanitized versions of such data; and (iii) provide privacy-preserving transparent access to sensitive contents by disclosing more or less information to readers according to their credentials toward the owner of the publications. We also study the applicability of the proposed system in general and illustrate its behavior in two case studies.

Investigation of Reasons of Social Media Usage of Physical Education and Sports School Students

“…Social network sites pave the way for a suitable environment in which individuals can share their personal information via communication networks (Jang et al 2016). These sites have evolved into an indispensable meeting point because it publishes information about millions of people (Viejo and Sanchez, 2016). "People tend to use the Internet and web applications more often owing to the rapid technological developments.…”

Measures of Privacy Protection on Social Environments

“…Information Content (IC) theory, which measures the inverse of the appearance probability of a term in a corpus, has been also used to distinguish between general and specific terms. This idea was used in [120,263] to propose a system for automatic semantic annotation by using knowledge bases and linguistic tools. Their system is able to make distinctions between values of the sensitivity of the information.…”

“…Other approaches [263,120] have considered preserving the users' privacy through the sanitization of the content shared. These research works use machine learning techniques to analyze textual posts, extract features of them, compute their sensitivity 2.3.…”

“…Currently, we have found several ways (from the literature works) to estimate information sensitivity. These approaches are mainly based on: (i) laws and regulations, referred to which types of users' information require more protection than others by companies that stores them [256]; (ii) market valuation, referred to the value of data from indicators such as the market revenues obtained per data record, the market prices for data, the cost of a data breach, and data prices in illegal markets [196,172]; (iii) individuals' valuation, referred to individual's willingness to pay to protect data [217,221]; and (iv) linguistics, referred to words-level analysis and frequency of appearance [263,120]. The comparison and implementation of a model that provides a combined approach of sensibility (adapted to online social networks domain) for the different information types could help to define better risk indicators.…”

“…The last approach considered is centered on linguistics and the use of words. According to Viejo et al [263], the terms that provide/disclose a large amount of information are also likely to be sensitive. In this respect, several privacy-protection methods for textual data and empirical studies have shown the close relationship between the informativeness of textual terms and their sensitivity [4,219].…”