Privacy is an enormous problem in online social networking sites. While sites such as Facebook allow users fine-grained control over who can see their profiles, it is difficult for average users to specify this kind of detailed policy. In this paper, we propose a template for the design of a social networking privacy wizard. The intuition for the design comes from the observation that real users conceive their privacy preferences (which friends should be able to see which information) based on an implicit set of rules. Thus, with a limited amount of user input, it is usually possible to build a machine learning model that concisely describes a particular user’s preferences, and then use this model to configure the user’s privacy settings automatically. As an instance of this general framework, we have built a wizard based on an active learning paradigm called uncertainty sampling. The wizard iteratively asks the user to assign privacy “labels ” to selected (“informative”) friends, and it uses this input to construct a classifier, which can in turn be used to automatically assign privileges to the rest of the user’s (unlabeled) friends. To evaluate our approach, we collected detailed privacy preference data from 45 real Facebook users. Our study revealed two important things. First, real users tend to conceive their privacy preferences in terms of communities, which can easily be extracted from a social network graph using existing techniques. Second, our active learning wizard, using communities as features, is able to recommend high-accuracy privacy settings using less user input than existing policy-specification tools.

Users of online social networking communities are disclosing large amounts of personal information, putting themselves at a variety of risks. Our ongoing research investigates mechanisms for socially appropriate privacy management in online social networking communities. As a first step, we are examining the role of interface usability in current privacy settings. In this paper we report on our first iterative prototype, where presenting an audienceoriented view of profile information significantly improved the understanding of privacy settings. 1.

The sharing of personal data has emerged as a popular activity over online social networking sites like Facebook. As a result, the issue of online social network privacy has received significant attention in both the research literature and the mainstream media. Our overarching goal is to improve defaults and provide better tools for managing privacy, but we are limited by the fact that the full extent of the privacy problem remains unknown; there is little quantification of the incidence of incorrect privacy settings or the difficulty users face when managing their privacy. In this paper, we focus on measuring the disparity between the desired and actual privacy settings, quantifying the magnitude of the problem of managing privacy. We deploy a survey, implemented as a Facebook application, to 200 Facebook users recruited via Amazon Mechanical Turk. We find that 36 % of content remains shared with the default privacy settings. We also find that, overall, privacy settings match users ’ expectations only 37 % of the time, and when incorrect, almost always expose content to more users than expected. Finally, we explore how our results have potential to assist users in selecting appropriate privacy settings by examining the user-created friend lists. We find that these have significant correlation with the social network, suggesting that information from the social network may be helpful in implementing new tools for managing privacy.

In recent years, social networking sites (SNSs) gained high popularity among Internet users as they combine the best of both worlds: befriending people outside real life situations and staying in touch with people already known. An important aspect of any SNS is user profiles, which allow users to virtually publish anything about themselves, including highly personal or sensitive information. With the inception of SNSs, the problem of personal information disclosure and privacy implications has turned into a serious issue. While privacy issues in SNSs have been extensively analyzed in the past five years showcasing flagships of “western ” SNSs like Facebook and MySpace, SNSs that target mainly Russian speaking audiences are not yet analyzed and demand investigation. The goals of this paper are twofold: (1) to raise the awareness of the public to the problems of information revelation by studying the amount and type of information disclosed by users of Runet (Russian Segment of the Internet) SNSs (2) to compare our findings to the results of previous studies in the context of “western ” SNSs. We investigate different aspects of information revelation of more than 30 million user profiles collected from five Runet SNSs considered in this paper. In addition, we conducted a survey among a Russian speaking population to assess both the level of awareness of the privacy issues and the level of trust, and compared the results to previous studies. While the results indicate that Runet users tend to disclose less information and are more concerned about privacy implications, there is still a substantial gap between western and Runet SNS providers in understanding of privacy implications and implementation of security measures, which leads to exposure of extensive amounts of personal information.

Privacy is a huge problem for users of social networking sites. While sites like Facebook allow individual users to personalize fine-grained privacy settings, this has proven quite difficult for average users. This demonstration illustrates a machine learning privacy wizard, or recommendation tool, that we have built at the University of Michigan. The wizard is based on the underlying observation that real users conceive their privacy preferences (which friends should see which data items) based on an implicit structure. Thus, using a limited amount of carefully-chosen user input, it is usually possible to build a machine learning model that accurately predicts the user’s privacy preferences. This model, in turn, can be used to recommend detailed privacy settings for the user. Our demonstration wizard runs as a thirdparty Facebook application. Conference attendees will be able to “test-drive ” the wizard by installing it on their own Facebook accounts. 1.

Thwarting large-scale crawls of user profiles in online social networks (OSNs) like Facebook and Renren is in the interest of both the users and the operators of these sites. OSN users wish to maintain control over their personal information, and OSN operators wish to protect their business assets and reputation. Existing rate-limiting techniques are ineffective against crawlers with many accounts, be they fake accounts (also known as Sybils) or compromised accounts of real users obtained on the black market. We propose Genie, a system that can be deployed by OSN operators to defend against crawlers in large-scale OSNs. Genie exploits the fact that the browsing patterns of honest users and crawlers are very different: even a crawler with access to many accounts needs to make many more profile views per account than an honest user, and view profiles of users that are more distant in the social network. Experiments using real-world data gathered from a popular OSN show that Genie frustrates large-scale crawling while rarely impacting honest users; the few honest users who are affected can recover easily by adding a few friend links.