اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدPrivacy-Preserving Data Publishing via Mutual Cover
283
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We study anonymization techniques for preserving privacy in the publication of microdata tables. Although existing approaches based on generalization can provide enough protection for identities, anonymized tables always suffer from various attribute disclosures because generalization is inefficient to protect sensitive values and the partition of equivalence groups is directly shown to the adversary. Besides, the generalized table also suffers from serious information loss because the original Quasi-Identifier (QI) values are hardly preserved and the protection against attribute disclosure often causes over-protection against identity disclosure. To this end, we propose a novel technique, called mutual cover, to hinder the adversary from matching the combination of QI values in microdata tables. The rationale is to replace the original QI values with random QI values according to some random output tables that make similar tuples to cover for each other at the minimal cost. As a result, the mutual cover prevents identity disclosure and attribute disclosure more effectively than generalization while retaining the distribution of original QI values as far as possible, and the information utility hardly decreases when enhancing the protection for sensitive values. The effectiveness of mutual cover is verified with extensive experiments.
قيم البحث
اقرأ أيضاً
Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. To address the privacy concerns of users in this environment, we propose a novel framework called PR-GAN
that offers privacy-preserving mechanism using generative adversarial networks. Given a target application, PR-GAN automatically modifies the data to hide sensitive attributes -- which may be hidden and can be inferred by machine learning algorithms -- while preserving the data utility in the target application. Unlike prior works, the publics possible knowledge of the correlation between the target application and sensitive attributes is built into our modeling. We formulate our problem as an optimization problem, show that an optimal solution exists and use generative adversarial networks (GAN) to create perturbations. We further show that our method provides privacy guarantees under the Pufferfish framework, an elegant generalization of the differential privacy that allows for the modeling of prior knowledge on data and correlations. Through experiments, we show that our method outperforms conventional methods in effectively hiding the sensitive attributes while guaranteeing high performance in the target application, for both property inference and training purposes. Finally, we demonstrate through further experiments that once our model learns a privacy-preserving task, such as hiding subjects identity, on a group of individuals, it can perform the same task on a separate group with minimal performance drops.
In the big data era, more and more cloud-based data-driven applications are developed that leverage individual data to provide certain valuable services (the utilities). On the other hand, since the same set of individual data could be utilized to in
fer the individuals certain sensitive information, it creates new channels to snoop the individuals privacy. Hence it is of great importance to develop techniques that enable the data owners to release privatized data, that can still be utilized for certain premised intended purpose. Existing data releasing approaches, however, are either privacy-emphasized (no consideration on utility) or utility-driven (no guarantees on privacy). In this work, we propose a two-step perturbation-based utility-aware privacy-preserving data releasing framework. First, certain predefined privacy and utility problems are learned from the public domain data (background knowledge). Later, our approach leverages the learned knowledge to precisely perturb the data owners data into privatized data that can be successfully utilized for certain intended purpose (learning to succeed), without jeopardizing certain predefined privacy (training to fail). Extensive experiments have been conducted on Human Activity Recognition, Census Income and Bank Marketing datasets to demonstrate the effectiveness and practicality of our framework.
Wearable devices generate different types of physiological data about the individuals. These data can provide valuable insights for medical researchers and clinicians that cannot be availed through traditional measures. Researchers have historically
relied on survey responses or observed behavior. Interestingly, physiological data can provide a richer amount of user cognition than that obtained from any other sources, including the user himself. Therefore, the inexpensive consumer-grade wearable devices have become a point of interest for the health researchers. In addition, they are also used in continuous remote health monitoring and sometimes by the insurance companies. However, the biggest concern for such kind of use cases is the privacy of the individuals. There are a few privacy mechanisms, such as abstraction and k-anonymity, are widely used in information systems. Recently, Differential Privacy (DP) has emerged as a proficient technique to publish privacy sensitive data, including data from wearable devices. In this paper, we have conducted a Systematic Literature Review (SLR) to identify, select and critically appraise researches in DP as well as to understand different techniques and exiting use of DP in wearable data publishing. Based on our study we have identified the limitations of proposed solutions and provided future directions.
As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and serving tasks in
the cloud, it is important to protect the privacy of sensitive samples in the training dataset and prevent information leakage to untrusted third parties. Past work have shown that a malicious machine learning service provider or end user can easily extract critical information about the training samples, from the model parameters or even just model outputs. In this paper, we propose a novel and generic methodology to preserve the privacy of training data in machine learning applications. Specifically we introduce an obfuscate function and apply it to the training data before feeding them to the model training task. This function adds random noise to existing samples, or augments the dataset with new samples. By doing so sensitive information about the properties of individual samples, or statistical properties of a group of samples, is hidden. Meanwhile the model trained from the obfuscated dataset can still achieve high accuracy. With this approach, the customers can safely disclose the data or models to third-party providers or end users without the need to worry about data privacy. Our experiments show that this approach can effective defeat four existing types of machine learning privacy attacks at negligible accuracy cost.
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.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
