IsIdentifiable: A tool for detecting identifiable information in data sources

Thomas Nind; Andrew Brooks; James Sutherland; Ruairidh MacLeod

IsIdentifiable: A tool for detecting identifiable information in data sources

Thomas Nind (Developer)
, Andrew Brooks (Developer)
, James Sutherland (Developer)
, Ruairidh MacLeod (Developer)

Research output: Non-textual form › Software

Abstract

A tool for detecting identifiable information in data sources. Out of the box supports:

- CSV
- DICOM
- Relational Database Tables (Sql Server, MySql, Postgres, Oracle)
- MongoDb

Rules base is driven by regular expressions and plugin services (e.g. Natural Language Processing). Also includes a reviewer/redactor tool for processing false positives and updating the rules base.
There is a standalone command line tool called ii for running directly or you can use the nuget package in your own code to evaluate data.

Original language	English
Place of Publication	United States
Publisher	GitHub
Media of output	Other
Size	Software
Publication status	Published - 2 Aug 2022

Keywords

NLP
csharp
anonymisation
natural language processing
tool
library
nuget

Access to Document

https://github.com/SMI/IsIdentifiableLicence: GNU GPL

Cite this

@misc{4aa26ea60b3a41f59a26248db3c9b254,

title = "IsIdentifiable: A tool for detecting identifiable information in data sources",

abstract = "A tool for detecting identifiable information in data sources. Out of the box supports: - CSV - DICOM - Relational Database Tables (Sql Server, MySql, Postgres, Oracle) - MongoDb Rules base is driven by regular expressions and plugin services (e.g. Natural Language Processing). Also includes a reviewer/redactor tool for processing false positives and updating the rules base. There is a standalone command line tool called ii for running directly or you can use the nuget package in your own code to evaluate data. ",

keywords = "NLP, csharp, anonymisation, natural language processing, tool, library, nuget",

author = "Thomas Nind and Andrew Brooks and James Sutherland and Ruairidh MacLeod",

year = "2022",

month = aug,

day = "2",

language = "English",

publisher = "GitHub",

address = "United States",

}

TY - ADVS

T1 - IsIdentifiable

T2 - A tool for detecting identifiable information in data sources

A2 - Nind, Thomas

A2 - Brooks, Andrew

A2 - Sutherland, James

A2 - MacLeod, Ruairidh

PY - 2022/8/2

Y1 - 2022/8/2

N2 - A tool for detecting identifiable information in data sources. Out of the box supports: - CSV - DICOM - Relational Database Tables (Sql Server, MySql, Postgres, Oracle) - MongoDb Rules base is driven by regular expressions and plugin services (e.g. Natural Language Processing). Also includes a reviewer/redactor tool for processing false positives and updating the rules base. There is a standalone command line tool called ii for running directly or you can use the nuget package in your own code to evaluate data.

AB - A tool for detecting identifiable information in data sources. Out of the box supports: - CSV - DICOM - Relational Database Tables (Sql Server, MySql, Postgres, Oracle) - MongoDb Rules base is driven by regular expressions and plugin services (e.g. Natural Language Processing). Also includes a reviewer/redactor tool for processing false positives and updating the rules base. There is a standalone command line tool called ii for running directly or you can use the nuget package in your own code to evaluate data.

KW - NLP

KW - csharp

KW - anonymisation

KW - natural language processing

KW - tool

KW - library

KW - nuget

M3 - Software

PB - GitHub

CY - United States

ER -

IsIdentifiable: A tool for detecting identifiable information in data sources

Abstract

Keywords

Access to Document

Fingerprint

Cite this