No abstract

Releasing full data records is one of the most challenging problems in data privacy. On the one hand, many of the popular techniques such as data de-identification are problematic because of their dependence on the background knowledge of adversaries. On the other hand, rigorous methods such as the exponential mechanism for differential privacy are often computationally impractical to use for releasing high dimensional data or cannot preserve high utility of original data due to their extensive data perturbation.This paper presents a criterion called plausible deniability that provides a formal privacy guarantee, notably for releasing sensitive datasets: an output record can be released only if a certain amount of input records are indistinguishable, up to a privacy parameter. This notion does not depend on the background knowledge of an adversary. Also, it can efficiently be checked by privacy tests. We present mechanisms to generate synthetic datasets with similar statistical properties to the input data and the same format. We study this technique both theoretically and experimentally. A key theoretical result shows that, with proper randomization, the plausible deniability mechanism generates differentially private synthetic data. We demonstrate the efficiency of this generative technique on a large dataset; it is shown to preserve the utility of original data with respect to various statistical analysis and machine learning measures.

No abstract

Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model. Prior work has shown that the attack is feasible when the model is overfitted to its training data or when the adversary controls the training algorithm. However, when the model is not overfitted and the adversary does not control the training algorithm, the threat is not well understood. In this paper, we report a study that discovers overfitting to be a sufficient but not a necessary condition for an MIA to succeed. More specifically, we demonstrate that even a well-generalized model contains vulnerable instances subject to a new generalized MIA (GMIA). In GMIA, we use novel techniques for selecting vulnerable instances and detecting their subtle influences ignored by overfitting metrics. Specifically, we successfully identify individual records with high precision in real-world datasets by querying black-box machine learning models. Further we show that a vulnerable record can even be indirectly attacked by querying other related records and existing generalization techniques are found to be less effective in protecting the vulnerable instances. Our findings sharpen the understanding of the fundamental cause of the problem: the unique influences the training instance may have on the model.

No abstract

HTTPS is the de facto standard for securing Internet communications. Although it is widely deployed, the security provided with HTTPS in practice is dubious. HTTPS may fail to provide security for multiple reasons, mostly due to certificate-based authentication failures. Given the importance of HTTPS, we investigate the current scale and practices of HTTPS and certificate-based deployment. We provide a large-scale empirical analysis that considers the top one million most popular websites. Our results show that very few websites implement certificatebased authentication properly. In most cases, domain mismatches between certificates and websites are observed. We study the economic, legal and social aspects of the problem. We identify causes and implications of the profit-oriented attitude of CAs and show how the current economic model leads to the distribution of cheap certificates for cheap security. Finally, we suggest possible changes to improve certificate-based authentication.

No abstract

To protect database confidentiality even in the face of full compromise while supporting standard functionality, recent academic proposals and commercial products rely on a mix of encryption schemes. The recommendation is to apply strong, semantically secure encryption to the "sensitive" columns and protect other columns with property-revealing encryption (PRE) that supports operations such as sorting. We design, implement, and evaluate a new methodology for inferring data stored in such encrypted databases. The cornerstone is the multinomial attack, a new inference technique that is analytically optimal and empirically outperforms prior heuristic attacks against PRE-encrypted data. We also extend the multinomial attack to take advantage of correlations across multiple columns. This recovers PREencrypted data with sufficient accuracy to then apply machine learning and record linkage methods to infer columns protected by semantically secure encryption or redaction. We evaluate our methodology on medical, census, and union-membership datasets, showing for the first time how to infer full database records. For PRE-encrypted attributes such as demographics and ZIP codes, our attack outperforms the best prior heuristic by a factor of 16. Unlike any prior technique, we also infer attributes, such as incomes and medical diagnoses, protected by strong encryption. For example, when we infer that a patient in a hospital-discharge dataset has a mental health or substance abuse condition, this prediction is 97% accurate.