@inproceedings{apparreddy-etal-2021-auditing,
title = "Auditing Keyword Queries Over Text Documents",
author = "Apparreddy, Bharath Kumar Reddy and
Rajanala, Sailaja and
Singh, Manish",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.46",
pages = "378--387",
abstract = "Data security and privacy is an issue of growing importance in the healthcare domain. In this paper, we present an auditing system to detect privacy violations for unstructured text documents such as healthcare records. Given a sensitive document, we present an anomaly detection algorithm that can find the top-k suspicious keyword queries that may have accessed the sensitive document. Since unstructured healthcare data, such as medical reports and query logs, are not easily available for public research, in this paper, we show how one can use the publicly available DBLP data to create an equivalent healthcare data and query log, which can then be used for experimental evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="apparreddy-etal-2021-auditing">
<titleInfo>
<title>Auditing Keyword Queries Over Text Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharath</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Apparreddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sailaja</namePart>
<namePart type="family">Rajanala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data security and privacy is an issue of growing importance in the healthcare domain. In this paper, we present an auditing system to detect privacy violations for unstructured text documents such as healthcare records. Given a sensitive document, we present an anomaly detection algorithm that can find the top-k suspicious keyword queries that may have accessed the sensitive document. Since unstructured healthcare data, such as medical reports and query logs, are not easily available for public research, in this paper, we show how one can use the publicly available DBLP data to create an equivalent healthcare data and query log, which can then be used for experimental evaluation.</abstract>
<identifier type="citekey">apparreddy-etal-2021-auditing</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.46</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>378</start>
<end>387</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Auditing Keyword Queries Over Text Documents
%A Apparreddy, Bharath Kumar Reddy
%A Rajanala, Sailaja
%A Singh, Manish
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F apparreddy-etal-2021-auditing
%X Data security and privacy is an issue of growing importance in the healthcare domain. In this paper, we present an auditing system to detect privacy violations for unstructured text documents such as healthcare records. Given a sensitive document, we present an anomaly detection algorithm that can find the top-k suspicious keyword queries that may have accessed the sensitive document. Since unstructured healthcare data, such as medical reports and query logs, are not easily available for public research, in this paper, we show how one can use the publicly available DBLP data to create an equivalent healthcare data and query log, which can then be used for experimental evaluation.
%U https://aclanthology.org/2021.icon-main.46
%P 378-387
Markdown (Informal)
[Auditing Keyword Queries Over Text Documents](https://aclanthology.org/2021.icon-main.46) (Apparreddy et al., ICON 2021)
ACL
- Bharath Kumar Reddy Apparreddy, Sailaja Rajanala, and Manish Singh. 2021. Auditing Keyword Queries Over Text Documents. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 378–387, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).