6 Hits in 8.0 sec

Information preservation in statistical privacy and bayesian estimation of unattributed histograms

Bing-Rong Lin, Daniel Kifer
2013 Proceedings of the 2013 international conference on Management of data - SIGMOD '13  
In statistical privacy, utility refers to two concepts: information preservation -how much statistical information is retained by a sanitizing algorithm, and usability -how (and with how much difficulty  ...  In particular, this result connects information preservation to aspects of usability -if the information preservation of a sanitizing algorithm should be measured as the average error of a Bayesian decision  ...  of utility in statistical privacy.  ... 
doi:10.1145/2463676.2463721 dblp:conf/sigmod/LinK13 fatcat:3yuqatzcrvh2jiq3qoxfsggemq

Differentially private anonymized histograms [article]

Ananda Theertha Suresh
2020 arXiv   pre-print
Anonymized histograms appear in various potentially sensitive contexts such as password-frequency lists, degree distribution in social networks, and estimation of symmetric properties of discrete distributions  ...  and the privacy parameter.  ...  Anonymized histograms are also referred to as histogram of histograms [1] , histogram order statistics [2] , profiles [3] , unattributed histograms [4] , fingerprints [5] , and frequency lists [6  ... 
arXiv:1910.03553v2 fatcat:bl5jyf5bt5byliuevwdtqeprve

Statistical Properties of Sanitized Results from Differentially Private Laplace Mechanism with Univariate Bounding Constraints [article]

Fang Liu
2019 arXiv   pre-print
Protection of individual privacy is a common concern when releasing and sharing data and information.  ...  Differential privacy (DP) formalizes privacy in probabilistic terms without making assumptions about the background knowledge of data intruders, and thus provides a robust concept for privacy protection  ...  Introduction Protection of individual privacy is always a concern when releasing and sharing information.  ... 
arXiv:1607.08554v5 fatcat:xjadkpr2b5elfbhchwkvku62za

Influence-directed Explanations for Machine Learning

Shayak Sen
Further, explanations can be used to support detection of privacy and fairness violations, as well as explain how they came about.  ...  We identify two major challenges to explaining information use in machine learning systems: (i) converged use, that machine learning systems typicallycombine a large number of input features, and (ii)  ...  Further, due to a result from [71] (and stated in [83] ), sampling amplifies the privacy of the computed statistic, allowing us to achieve high privacy with minimal noise addition.  ... 
doi:10.1184/r1/16860118 fatcat:5znrdfvstvcchbdf4s4jwf7ep4

A Survey of Insider Attack Detection Research [chapter]

Malek Ben Salem, Shlomo Hershkop, Salvatore J. Stolfo
Advances in Information Security  
This paper surveys proposed solutions for the problem of insider attack detection appearing in the computer security research literature.  ...  We distinguish between masqueraders and traitors as two distinct cases of insider attack.  ...  Hence, we also believe that any technologies developed to detect insider attack have to include strong privacy-preserving guarantees to avoid making false claims that could harm the reputation of individuals  ... 
doi:10.1007/978-0-387-77322-3_5 fatcat:3zvvdjjnunfnve3vemmf47syea

CollAboRation - Opportunities of augmented reality for novel interaction paradigms and communication research

Alexander Neumann
Statistical differences concerning the use of head gestures, mediation object handling, body posture, and speech activity between AR and face-to-face conditions or between assisted and base conditions  ...  The central part of this thesis is dedicated to the second funding phase of the interdisciplinary project Alignment in AR-based cooperation (AlARCo).  ...  Acknowledgments Journal articles and peer-reviewed conference papers  ... 
doi:10.4119/unibi/2964199 fatcat:nrstp7ja2fgajojafdvi5trb44