No abstract

Online social networks, such as Facebook, are increasingly utilized by many users. These networks allow people to publish details about themselves and connect to their friends. Some of the information revealed inside these networks is private and it is possible that corporations could use learning algorithms on the released data to predict undisclosed private information. In this paper, we propose an effective, scalable inference attack for released social networking data to infer undisclosed private information about individuals. We then explore the effectiveness of possible sanitization techniques that can be used to combat such an inference attack.

On-line social networks, such as Facebook, are increasingly utilized by many people. These networks allow users to publish details about themselves and connect to their friends. Some of the information revealed inside these networks is meant to be private. Yet it is possible that corporations could use learning algorithms on released data to predict undisclosed private information. In this paper, we explore how to launch inference attacks using released social networking data to predict undisclosed private information about individuals. We then devise three possible sanitization techniques that could be used in various situations. Then, we explore the effectiveness of these techniques by implementing them on a dataset obtained from the Dallas/Fort Worth, Texas network of the Facebook social networking application and attempting to use methods of collective inference to discover sensitive attributes of the data set. We show that we can decrease the effectiveness of both local and relational classification algorithms by using the sanitization methods we described. Further, we discover a problem domain where collective inference degrades the performance of classification algorithms for determining private attributes.

No abstract

Our software for secure meta-analysis of genetic association studies, SecureMA, is publicly available at http://github.com/XieConnect/SecureMA. Our customized secure computation framework is also publicly available at http://github.com/XieConnect/CircuitService.

Health information technologies facilitate the collection of massive quantities of patient-level data. A growing body of research demonstrates that such information can support novel, large-scale biomedical investigations at a fraction of the cost of traditional prospective studies. While healthcare organizations are being encouraged to share these data in a de-identified form, there is hesitation over concerns that it will allow corresponding patients to be re-identified. Currently proposed technologies to anonymize clinical data may make unrealistic assumptions with respect to the capabilities of a recipient to ascertain a patients identity. We show that more pragmatic assumptions enable the design of anonymization algorithms that permit the dissemination of detailed clinical profiles with provable guarantees of protection. We demonstrate this strategy with a dataset of over one million medical records and show that 192 genotype-phenotype associations can be discovered with fidelity equivalent to non-anonymized clinical data.

Given the potential wealth of insights in personal data the big databases can provide, many organizations aim to share data while protecting privacy by sharing de-identified data, but are concerned because various demonstrations show such data can be re-identified. Yet these investigations focus on how attacks can be perpetrated, not the likelihood they will be realized. This paper introduces a game theoretic framework that enables a publisher to balance re-identification risk with the value of sharing data, leveraging a natural assumption that a recipient only attempts re-identification if its potential gains outweigh the costs. We apply the framework to a real case study, where the value of the data to the publisher is the actual grant funding dollar amounts from a national sponsor and the re-identification gain of the recipient is the fine paid to a regulator for violation of federal privacy rules. There are three notable findings: 1) it is possible to achieve zero risk, in that the recipient never gains from re-identification, while sharing almost as much data as the optimal solution that allows for a small amount of risk; 2) the zero-risk solution enables sharing much more data than a commonly invoked de-identification policy of the U.S. Health Insurance Portability and Accountability Act (HIPAA); and 3) a sensitivity analysis demonstrates these findings are robust to order-of-magnitude changes in player losses and gains. In combination, these findings provide support that such a framework can enable pragmatic policy decisions about de-identified data sharing.

Organizations share data about individuals to drive business and comply with law and regulation. However, an adversary may expose confidential information by tracking an individual across disparate data publications using quasi-identifying attributes (e.g., age, geocode and sex) associated with the records. Various studies have shown that well-established privacy protection models (e.g., k-anonymity and its extensions) fail to protect an individual’s privacy against this “composition attack”. This type of attack can be thwarted when organizations coordinate prior to data publication, but such a practice is not always feasible. In this paper, we introduce a probabilistic model called (d, α)-linkable, which mitigates composition attack without coordination. The model ensures that d confidential values are associated with a quasi-identifying group with a likelihood of α. We realize this model through an efficient extension to k-anonymization and use extensive experiments to show our strategy significantly reduces the likelihood of a successful composition attack and can preserve more utility than alternative privacy models, such as differential privacy.