scholarly journals DPSyn: Experiences in the NIST Differential Privacy Data Synthesis Challenges

2021 ◽  
Vol 11 (2) ◽  
Author(s):  
Tianhao Wang ◽  
Ninghui Li ◽  
Zhikun Zhang
Keyword(s):  
Differential Privacy ◽  
Research Community ◽  
Theory And Practice ◽  
Data Synthesis

We summarize the experience of participating in two differential privacycompetitions organized by the National Institute of Standards and Technology (NIST). Inthis paper, we document our experiences in the competition, the approaches we have used,the lessons we have learned, and our call to the research community to further bridge thegap between theory and practice in DP research.

scholarly journals Methodologies of continuous improvement between theory and practice (Quality, Excellence Model, Kaizen) Model

2021 ◽  
pp. 105-132
Author(s):  
محمد حسن البخيت
Keyword(s):  
Data Collection ◽  
Social Science ◽  
Random Sample ◽  
Statistical Methods ◽  
Continuous Improvement ◽  
Descriptive Study ◽  
Research Community ◽  
Theory And Practice ◽  
Government Institutions ◽  
Descriptive Approach

This study dealt with the topic (methodologies of continuous improvement between theory and practice) - quality, excellence model, Kaizen - model, descriptive study on a sample of institutions in the state of Khartoum - Sudan. Which aims to know whether government institutions apply methodologies of continuous improvement or not, and support and motivate them to apply these methodologies and work to spread awareness to become a general culture among employees. The researcher followed the descriptive approach, as he used a number of data collection tools in scientific research, observation, interview and the questionnaire newspaper, and a stratified random sample was selected for (50) individuals from five institutions, each institution has ten individuals representing the entire research community, and the questionnaire was distributed Through the researcher personally. It was analyzed on a computer by the statistical package for social science (spss). Using statistical methods:

scholarly journals Remembering Why: The Role of Story in Educational Research

in education ◽  
2013 ◽  
Vol 17 (2) ◽  
Author(s):  
Marni Binder
Keyword(s):  
Inner City ◽  
Educational Research ◽  
Professional Practice ◽  
Teaching And Learning ◽  
Research Community ◽  
Research Tool ◽  
Theory And Practice ◽  
Teaching And Research ◽  
Powerful Research Tool

This paper examines the role of story in educational research as an empowering method of inquiry. By stepping back and remembering why, the author retells a professional story of practice between her and a colleague, exploring Vivian Gussin Paley’s story play in a Grade 1/2 inner city classroom. Moving in and through past and present experiences illustrates the need for story in researching professional practice, the significance of story as a powerful research tool, and the profound understanding of teaching and learning that unfolds as a result of such collaborations. Story creates an ethos in the teaching and research community, uniting theory and practice into a visible partnership.Keywords: story; educational research; theory and practice

scholarly journals Special Issue on the Theory and Practice of Differential Privacy

2017 ◽  
Vol 7 (2) ◽  
Author(s):  
Marco Gaboardi ◽  
Chris J. Skinner
Keyword(s):  
Data Analysis ◽  
Programming Languages ◽  
Differential Privacy ◽  
International Workshop ◽  
Theory And Practice ◽  
Release Mechanism ◽  
Special Issue ◽  
Research Areas ◽  
Recent Developments ◽  
Definition Of

This special issue presents papers based on contributions to the first international workshop on the “Theory and Practice of Differential Privacy” (TPDP) held in London, UK, 18 April 2015, as part of the European joint conference on Theory And Practice of Software (ETAPS). Differential privacy is a mathematically rigorous definition of the privacy protection provided by a data release mechanism: it offers a strong guaranteed bound on what can be learned about a user as a result of participating in a differentially private data analysis. Researchers in differential privacy come from several areas of computer science, including algorithms, programming languages, security, databases and machine learning, as well as from several areas of statistics and data analysis. The workshop was intended to be an occasion for researchers from these different research areas to discuss the recent developments in the theory and practice of differential privacy. The program of the workshop included 10 contributed talks, 1 invited speaker and 1 joint invited speaker with the workshop “Hot Issues in Security Principles and Trust” (HotSpot 2016). Participants at the workshop were invited to submit papers to this special issue. Six papers were accepted, most of which directly reflect talks presented at the workshop

scholarly journals Editorial for Volume 9 Issue 2

2019 ◽  
Vol 9 (2) ◽  
Author(s):  
Jonathan Ullman ◽  
Lars Vilhuber
Keyword(s):  
Social Sciences ◽  
Computer Security ◽  
Programming Languages ◽  
Differential Privacy ◽  
Census Bureau ◽  
Theory And Practice ◽  
Mining Machine ◽  
Special Issue ◽  
Worst Case ◽  
High Degree

Differential privacy is a promising approach to privacy-preserving data analysis that provides strong worst-case guarantees about the harm that a user could suffer from contributing their data, but is also flexible enough to allow for a wide variety of data analyses to be performed with a high degree of utility. Researchers in differential privacy span many distinct research communities, including algorithms, computer security, cryptography, databases, data mining, machine learning, statistics, programming languages, social sciences, and law. Two articles in this issue describe applications of differentially private, or nearly differentially private, algorithms to data from the U.S. Census Bureau. A  third article highlights a thorny issue that applies to all implementations of differential privacy: how to choose the key privacy parameter ε, This special issue also includes selected contributions from the 3rd Workshop on Theory and Practice of Differential Privacy, which was held in Dallas, TX on October 30, 2017 as part of the ACM Conference on Computer Security (CCS).

scholarly journals Service action research: review and guidelines

2020 ◽  
Vol 34 (1) ◽  
pp. 87-99 ◽  
Author(s):  
Mattias Elg ◽  
Ida Gremyr ◽  
Árni Halldórsson ◽  
Andreas Wallo
Keyword(s):  
Action Research ◽  
Community Action ◽  
Research Community ◽  
Theory And Practice ◽  
Research Quality ◽  
Research Review ◽  
Service Research ◽  
Action Research Project ◽  
Content Type ◽  
Conducting Research

Purpose Conducting research that is both practice- and theory-relevant is important for the service research community. Action research can be a fruitful approach for service researchers studying the transformative role of service research and wanting to make contributions to both the research community and to practical development. By exploring the current use of action research in service research, this study aims to make suggestions for enhancing the contribution to theory and practice development and to propose criteria for research quality for action research in service research. Design/methodology/approach This study builds on a systematic literature review of the use of action research approaches in service research. Findings The study makes three main contributions. First, it posits that any action research project needs to consider the four elements of problem identification, theorization, creating guiding concepts and intervention. Second, based on these elements mirrored in service action research, it outlines and analyzes three approaches to action research (i.e. theory-enhancing, concept developing and practice-enhancing). Third, it suggests a move from instrumental to a more conceptual relevance of the research and elaborates on the criteria for research quality. Originality/value This study contributes to the understanding of how action research may be applied for conducting high-quality collaborative research in services and proposes measures to enhance research quality in action research projects focusing services.

scholarly journals Conceptualising quality in co-produced research

2020 ◽  
pp. 146879412091909
Author(s):  
Marilyn Howard ◽  
Helen Thomas-Hughes
Keyword(s):  
Knowledge Production ◽  
Research Process ◽  
Research Community ◽  
Early Career ◽  
Theory And Practice ◽  
Research Quality ◽  
Policy Studies ◽  
Early Career Researchers ◽  
Process Outcomes ◽  
Key Dimensions

Co-produced research is said to create new knowledge through including the perspectives of those traditionally excluded from knowledge production, which in turn is expected to enhance research quality and impact. This article critically examines academic and UK voluntary sector literature concerning participatory and co-produced approaches to explore how quality is currently understood in co-produced research. Drawing on early career researchers’ experiences of a programme of co-produced research, the authors illustrate how theory and practice of co-production can differ, and the implications for conceptualising ‘research quality’ within co-produced research. Drawing on debates within qualitative research, community work and policy studies, the article outlines a potential framework for raising questions of ‘quality’, co-produced by research partners as part of the research process. Key dimensions of this framework are process, outcomes and autonomy.

scholarly journals Editorial for Special Issue on the Theory and Practice of Differential Privacy 2018

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Aleksandar Nikolov ◽  
Lars Vilhuber
Keyword(s):  
Computer Security ◽  
Differential Privacy ◽  
Theory And Practice ◽  
Special Issue

This special issue  includes selected contributions from the 4th Workshop on Theory and Practice of Differential Privacy, which was held in Toronto, Canada on 15 October 2018 as part of the ACM Conference on Computer Security (CCS).

Kamino

2021 ◽  
Vol 14 (10) ◽  
pp. 1886-1899
Author(s):  
Chang Ge ◽  
Shubhankar Mohapatra ◽  
Xi He ◽  
Ihab F. Ilyas
Keyword(s):  
Differential Privacy ◽  
State Of The Art ◽  
Synthesis Methods ◽  
Sensitive Information ◽  
Synthesis System ◽  
Data Synthesis ◽  
Generative Process ◽  
Original Dataset ◽  
Private Data ◽  
Data Owner

Organizations are increasingly relying on data to support decisions. When data contains private and sensitive information, the data owner often desires to publish a synthetic database instance that is similarly useful as the true data, while ensuring the privacy of individual data records. Existing differentially private data synthesis methods aim to generate useful data based on applications, but they fail in keeping one of the most fundamental data properties of the structured data --- the underlying correlations and dependencies among tuples and attributes (i.e., the structure of the data). This structure is often expressed as integrity and schema constraints, or with a probabilistic generative process. As a result, the synthesized data is not useful for any downstream tasks that require this structure to be preserved. This work presents KAMINO, a data synthesis system to ensure differential privacy and to preserve the structure and correlations present in the original dataset. KAMINO takes as input of a database instance, along with its schema (including integrity constraints), and produces a synthetic database instance with differential privacy and structure preservation guarantees. We empirically show that while preserving the structure of the data, KAMINO achieves comparable and even better usefulness in applications of training classification models and answering marginal queries than the state-of-the-art methods of differentially private data synthesis.

Data synthesis via differentially private markov random fields

2021 ◽  
Vol 14 (11) ◽  
pp. 2190-2202
Author(s):  
Kuntai Cai ◽  
Xiaoyu Lei ◽  
Jianxin Wei ◽  
Xiaokui Xiao
Keyword(s):  
Markov Random Fields ◽  
Input Data ◽  
Differential Privacy ◽  
State Of The Art ◽  
Synthetic Data ◽  
The State ◽  
High Dimensional ◽  
Data Synthesis ◽  
Markov Random ◽  
Low Dimensional

This paper studies the synthesis of high-dimensional datasets with differential privacy (DP). The state-of-the-art solution addresses this problem by first generating a set M of noisy low-dimensional marginals of the input data D , and then use them to approximate the data distribution in D for synthetic data generation. However, it imposes several constraints on M that considerably limits the choices of marginals. This makes it difficult to capture all important correlations among attributes, which in turn degrades the quality of the resulting synthetic data. To address the above deficiency, we propose PrivMRF, a method that (i) also utilizes a set M of low-dimensional marginals for synthesizing high-dimensional data with DP, but (ii) provides a high degree of flexibility in the choices of marginals. The key idea of PrivMRF is to select an appropriate M to construct a Markov random field (MRF) that models the correlations among the attributes in the input data, and then use the MRF for data synthesis. Experimental results on four benchmark datasets show that PrivMRF consistently outperforms the state of the art in terms of the accuracy of counting queries and classification tasks conducted on the synthetic data generated.

Sign in / Sign up

Export Citation Format

Share Document