Key stroke profiling for data loss prevention

Jain Shing Wu; Yuh-Jye Lee; Song Kong Chong; Chih Ta Lin; Jung Lun Hsu

doi:10.1109/TAAI.2013.16

Key stroke profiling for data loss prevention

Jain Shing Wu, Yuh-Jye Lee, Song Kong Chong, Chih Ta Lin, Jung Lun Hsu

Department of Applied Mathematics

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

Data leakage has become a serious problem to many organizations. To provide visibility into what data is confidential and where it's stored, many of current data leakage prevention (DLP) solutions depend on scanning file content. This approach needs the capability of parsing various file formats, but for those unsupported file formats there still exist risks of data breach. To address this issue, this study proposes an active DLP model by hooking on keyboard API to track and profile user key stroke behaviour. This has two major advantages: (1) It can discover sensitive data without parsing file formats, and (2) A data creator can be identified according to his/her key stroke behaviour. Since this model is based on key stroke profiling, it can resolve unsupported file format issue and have the capability of file creator identification.

Original language	English
Pages	7-12
Number of pages	6
DOIs	https://doi.org/10.1109/TAAI.2013.16
State	Published - 2013
Event	2013 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2013 - Taipei, Taiwan Duration: 6 Dec 2013 → 8 Dec 2013

Conference

Conference	2013 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2013
Country/Territory	Taiwan
City	Taipei
Period	6/12/13 → 8/12/13

Keywords

Data leakage prevention
File parser
Key stroke profiling
Sensitive data protection

Access to Document

10.1109/TAAI.2013.16

Cite this

@conference{dc54fcd1580f473f9cec43b37ae918ff,

title = "Key stroke profiling for data loss prevention",

abstract = "Data leakage has become a serious problem to many organizations. To provide visibility into what data is confidential and where it's stored, many of current data leakage prevention (DLP) solutions depend on scanning file content. This approach needs the capability of parsing various file formats, but for those unsupported file formats there still exist risks of data breach. To address this issue, this study proposes an active DLP model by hooking on keyboard API to track and profile user key stroke behaviour. This has two major advantages: (1) It can discover sensitive data without parsing file formats, and (2) A data creator can be identified according to his/her key stroke behaviour. Since this model is based on key stroke profiling, it can resolve unsupported file format issue and have the capability of file creator identification.",

keywords = "Data leakage prevention, File parser, Key stroke profiling, Sensitive data protection",

author = "Wu, {Jain Shing} and Yuh-Jye Lee and Chong, {Song Kong} and Lin, {Chih Ta} and Hsu, {Jung Lun}",

year = "2013",

doi = "10.1109/TAAI.2013.16",

language = "English",

pages = "7--12",

note = "2013 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2013 ; Conference date: 06-12-2013 Through 08-12-2013",

}

TY - CONF

T1 - Key stroke profiling for data loss prevention

AU - Wu, Jain Shing

AU - Lee, Yuh-Jye

AU - Chong, Song Kong

AU - Lin, Chih Ta

AU - Hsu, Jung Lun

PY - 2013

Y1 - 2013

N2 - Data leakage has become a serious problem to many organizations. To provide visibility into what data is confidential and where it's stored, many of current data leakage prevention (DLP) solutions depend on scanning file content. This approach needs the capability of parsing various file formats, but for those unsupported file formats there still exist risks of data breach. To address this issue, this study proposes an active DLP model by hooking on keyboard API to track and profile user key stroke behaviour. This has two major advantages: (1) It can discover sensitive data without parsing file formats, and (2) A data creator can be identified according to his/her key stroke behaviour. Since this model is based on key stroke profiling, it can resolve unsupported file format issue and have the capability of file creator identification.

AB - Data leakage has become a serious problem to many organizations. To provide visibility into what data is confidential and where it's stored, many of current data leakage prevention (DLP) solutions depend on scanning file content. This approach needs the capability of parsing various file formats, but for those unsupported file formats there still exist risks of data breach. To address this issue, this study proposes an active DLP model by hooking on keyboard API to track and profile user key stroke behaviour. This has two major advantages: (1) It can discover sensitive data without parsing file formats, and (2) A data creator can be identified according to his/her key stroke behaviour. Since this model is based on key stroke profiling, it can resolve unsupported file format issue and have the capability of file creator identification.

KW - Data leakage prevention

KW - File parser

KW - Key stroke profiling

KW - Sensitive data protection

UR - http://www.scopus.com/inward/record.url?scp=84899449814&partnerID=8YFLogxK

U2 - 10.1109/TAAI.2013.16

DO - 10.1109/TAAI.2013.16

M3 - Paper

AN - SCOPUS:84899449814

SP - 7

EP - 12

T2 - 2013 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2013

Y2 - 6 December 2013 through 8 December 2013

ER -

Key stroke profiling for data loss prevention

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this