ebook ebooks e-book e-books downloaden bei MyEbooks.ch downloaden

Privacy and Anonymity in Information Management Systems New Techniques for New Practical Problems

:	Jordi Nin, Javier Herranz
:	Jordi Nin, Javier Herranz
:	Privacy and Anonymity in Information Management Systems New Techniques for New Practical Problems
:	Springer-Verlag
:	9781849962384
:	Advanced Information and Knowledge Processing
:	1
:	CHF 133.60
:

:	Informatik
:	English

:	198
:	Wasserzeichen/DRM
:	PC/MAC/eReader/Tablet
:	PDF

As depicted in David Lodge's celebrated novel Small World, the perceived size of our world experienced a progressive decrease as jet airplanes became affordable to ever greater shares of the earth's population. Yet, the really dramatic shrinking had to wait until the mid-1990s, when Internet became widespread and the information age stopped being an empty buzzword. But small is not necessarily beautiful. We now live in a global village and, alas, some (often very powerful) voices state that we ought not expect any more privacy in it. Should this be true, we would have created our own nightmare: a global village combining the worst of conventional villages, where a lot of information on an individual is known by the other villagers, and conventional big cities, where the invidual feels lost in a grim and potentially dangerous place. Whereas security is essential for organizations to survive, individuals and so- times even companies also need some privacy to develop comfortably and lead a free life. This is the reason why individual privacy is mentioned in the Univ- sal Declaration of Human Rights (1948) and data privacy is protected by law in most Western countries. Indeed, without privacy, the rest of fundamental rights, like freedom of speech and democracy, are impaired. The outstanding challenge is to create technology that implements those legal guarantees in a way compatible with functionality and security. This book edited by Dr. Javier Herranz and Dr.

Jordi Nin (Barcelona, Catalonia, 1979; BSc 2004, MSc 2007, PhD 2008 all in Computer Science) is a post-doctoral researcher at the Artificial Intelligence Research Institute (IIIA-CSIC) near Barcelona, Catalonia, Spain. His fields of interest are privacy technologies, machine learning and soft computing tools. He has been involved in several research projects funded by the Catalan and Spanish governments and the European Community. His research has been published in specialized journals and major conferences (around 30 papers). Javier Herranz obtained his PhD in Applied Mathematics in 2005, in the Technial University of Catalonia (UPC, Barcelona, Spain). After that he spent 9 months in the Ecole Polytechnique (France) and 9 months in the Centrum voor Wiskunde en Informatica (CWI, The Netherlands), as a post-doctoral researcher, granted with an ERCIM fellowship. From January 2007, he works as a post-doctoral researcher at IIIA-CSIC (Bellaterra, Spain). His research interests include the design and analysis of cryptographic protols and the study of privacy preserving operations involving databases.

	Foreword	6
	Acknowledgments	8
	Contents	9
	Contributors	11
	Part I Overview	13
	1 Introduction to Privacy and Anonymity in Information Management Systems	14
	1.1 Background and Motivation	14
	1.2 Organization of the Book	15
	1.2.1 Part II: Theory of SDC	15
	1.2.2 Part III: Preserving Privacy in Distributed Applications	16
	2 Advanced Privacy-Preserving Data Managementand Analysis	18
	2.1 Introduction	18
	2.2 Managing Anonymized Data	20
	2.2.1 Randomization-Based Anonymization Techniques	20
	2.2.2 Aggregation-Based Anonymization Techniques	22
	2.3 Managing Time-Varying Anonymized Data	23
	2.3.1 Anonymizing Multiple Releases	24
	2.3.2 Anonymizing Data Streams	26
	2.4 Privacy-Preserving Data Analysis (PPDA)	27
	2.4.1 Privacy-Preserving Association Rule Mining	27
	2.4.2 Privacy-Preserving Classification	29
	2.4.3 Privacy-Preserving Clustering	33
	2.5 Conclusions	35
	References	36
	Part II Theory of SDC	39
	3 Practical Applications in Statistical Disclosure ControlUsing R	40
	3.1 Microdata Protection Using sdcMicro	40
	3.1.1 Software Issues	41
	3.1.2 The sdcMicro GUI	41
	3.1.3 Anonymization of Categorical Variables	43
	3.1.4 Anonymization of Numerical Variables	52
	3.1.5 Disclosure Risk	55
	3.1.6 Case Study Using Real-World Data	57
	3.2 Tabular Data Protection Using sdcTable	59
	3.2.1 Frequency and Magnitude Tables	59
	3.2.2 Primary Sensitive Cells	60
	3.2.3 Secondary Cell Suppression	61
	3.2.4 Software Issues	61
	3.2.5 Anonymizing Tables Using sdcTable -- A Guided Tour	63
	3.2.6 Summary	68
	3.3 Summary	68
	References	69
	4 Disclosure Risk Assessment for Sample Microdata Through Probabilistic Modeling	72
	4.1 Introduction	72
	4.2 Disclosure Risk Measures and Their Estimation	75
	4.2.1 Notation and Definitions	75
	4.2.2 Estimating the Disclosure Risk	76
	4.2.3 Model Selection and Goodness-of-Fit Criteria	78
	4.3 Complex Survey Designs	80
	4.4 Measurement Error Models for Disclosure Risk Measures	81
	4.5 Variance Estimation for Global Disclosure Risk Measures	83
	4.6 Examples of Applications	85
	4.6.1 Estimating Disclosure Risk Measures Under No Misclassification	85
	4.6.2 Estimating Disclosure Risk Measures Under Misclassification	90
	4.6.3 Variance Estimation and Confidence Intervals	93
	4.7 Extensions to Probabilistic Modeling for Disclosure Risk Estimation	93
	References	97
	5 Exploiting Auxiliary Information in the Estimation of Per-Record Risk of Disclosure	99
	5.1 Introduction	100
	5.2 Risk Measures and Models for Risk Estimation	101
	5.2.1 Superpopulation Models for Risk Estimation with Survey Data	102
	5.2.2 SPREE-Type Estimators for Cross-Classifications	104
	5.3 Simulation Plan and Data	108
	5.4 Risk Estim