Knowledge Base Distortion to Guarantee Data Privacy
نویسنده
چکیده
The problem of data privacy is to verify that confidential information stored in an information system is not provided to unauthorized users and, therefore, personal and other sensitive data remain private. One way to guarantee this is to distort a knowledge base such that it does not reveal sensitive information. In the present paper we will give a definition of the problem of knowledge base distortion that is independent of any knowledge representation formalism. We will then present a basic and general algorithm for knowledge base distortion to guarantee data privacy. This algorithm provides us with upper bounds for the complexity of the distortion problem. Moreover, we examine heuristics to improve its average performance.
منابع مشابه
A Universal Approach to Guarantee Data Privacy
The problem of data privacy is to verify that confidential information stored in an information system is not provided to unauthorized users and, therefore, personal and other sensitive data remain private. One way to guarantee this is to distort a knowledge base such that it does not reveal sensitive information. In the present paper we will give a universal definition of the problem of knowle...
متن کاملA novel data distortion approach via selective SSVD for privacy protection
Accurate knowledge extracted from relevant datasets is essential for making reasonable and timely decisions using data mining algorithms. In order to both guarantee data quality collected and prevent disclosure of confidential or sensitive information, privacy preservation has become a major concern in the design of practical data mining applications. In this paper, a novel data distortion appr...
متن کاملPrivacy Games: Optimal User-Centric Data Obfuscation
Consider users who share their data (e.g., location) with an untrusted service provider to obtain a personalized (e.g., location-based) service. Data obfuscation is a prevalent user-centric approach to protecting users’ privacy in such systems: the untrusted entity only receives a noisy version of user’s data. Perturbing data before sharing it, however, comes at the price of the users’ utility ...
متن کاملA privacy preserving technique for distance-based classification with worst case privacy guarantees
There has been relatively little work on privacy preserving techniques for distance based mining. The most widely used ones are additive perturbation methods and orthogonal transform based methods. These methods concentrate on privacy protection in the average case and provide no worst case privacy guarantee. However, the lack of privacy guarantee makes it difficult to use these techniques in p...
متن کاملDifferentially Private Password Frequency Lists
Given a dataset of user-chosen passwords, the frequency list reveals the frequency of each unique password. We present a novel mechanism for releasing perturbed password frequency lists with rigorous security, efficiency, and distortion guarantees. Specifically, our mechanism is based on a novel algorithm for sampling that enables an efficient implementation of the exponential mechanism for dif...
متن کامل