Cor-Split: Defending Privacy in Data Re-publication from Historical Correlations and Compromised Tuples
نویسندگان
چکیده
Experimental setup: • Dataset: Real census data (http://ipums.org/) composed of 600,000 tuples. Each tuple stores information about an individual: 4 QI-attributes and one private attribute having 50 possible values. Insertions and deletions were randomly performed to obtain a history of 21 releases. • Parameters: p = 0.04; m = 6; L = 21; h = 0.1. Given these parameters, the level n of (m,n)-historical safety to be enforced was n = 3.
منابع مشابه
Precision-bounded Access Control for Privacy-preserving Data Streams
Access control mechanisms and Privacy Protection Mechanisms (PPM) have been proposed for data streams. The access control for data stream allows roles access to tuples satisfying an authorized predicate sliding-window query. When the sensitive stream data is shared without a PPM the privacy can be compromised. The PPM meets privacy requirements, e.g., k-anonymity or l-diversity by generalizatio...
متن کاملOLAP Means On-Line Anti-Privacy∗
In this paper we investigate the privacy breaches caused by multi-dimensional range sum queries in OLAP (Online Analytic Processing) systems. Our results show that the sensitive information stored in the underlying data warehouses can be easily compromised by malicious users with legitimate range queries. This compromise is possible even when users are restricted to some special class of range ...
متن کاملانتشار تکراری: چالشی رو به رشد
During several years of cooperation with scientific journals in Iran as referee, member of editorial boards and editor in chief, I have faced with multiple non-ethical behaviors in publication. These days, I am witnessed to submitting articles to two or more journal simultaneously. Due to the growing pattern of this illegal action, this editorial will assess its dimensions and consequences....
متن کاملThe Impact of Official Publication of Information in Tehran Stock Exchange on Shares Prices: A GMM Approach
Released information in stock markets plays an important role in making decisions by agents like brokers, investors and other market activists. Rational decision-making in these markets will be possible if relevant and significant information is being released on-time. Otherwise, transparency and equality in the market is compromised. This study aims to respond to the question of whether offici...
متن کاملDefending against Attribute-Correlation Attacks in Privacy-Aware Information Brokering
Nowadays, increasing needs for information sharing arise due to extensive collaborations among organizations. Organizations desire to provide data access to their collaborators while preserving full control over the data and comprehensive privacy of their users. A number of information systems have been developed to provide efficient and secure information sharing. However, most of the solution...
متن کامل