Detecting Anomalies in Graphs with Numeric Labels

Michael Davis; Weiru Liu; Paul Miller; George Redpath

doi:10.1145/2063576.2063749

Detecting Anomalies in Graphs with Numeric Labels

Michael Davis, Weiru Liu, Paul Miller, George Redpath

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

36 Citations (Scopus)

Abstract

This paper presents Yagada, an algorithm to search labelled graphs for anomalies using both structural data and numeric attributes. Yagada is explained using several security-related examples and validated with experiments on a physical Access Control database. Quantitative analysis shows that in the upper range of anomaly thresholds, Yagada detects twice as many anomalies as the best-performing numeric discretization algorithm. Qualitative evaluation shows that the detected anomalies are meaningful, representing a com- bination of structural irregularities and numerical outliers.

Original language	English
Pages	1197-1202
Number of pages	6
DOIs	https://doi.org/10.1145/2063576.2063749
Publication status	Published - Oct 2011
Event	20th ACM Conference on Information and Knowledge Management - Glasgow, United Kingdom Duration: 24 Oct 2011 → 28 Oct 2011

Conference

Conference	20th ACM Conference on Information and Knowledge Management
Abbreviated title	CIKM 2011
Country/Territory	United Kingdom
City	Glasgow
Period	24/10/2011 → 28/10/2011

Bibliographical note

ISSN: 978-1-4503-0717-8

Access to Document

10.1145/2063576.2063749

R1118ECI: Centre for Secure Information Technologies (CSIT)
McCanny, J. V. (PI), Cowan, C. (CoI), Crookes, D. (CoI), Fusco, V. (CoI), Linton, D. (CoI), Liu, W. (CoI), Miller, P. (CoI), O'Neill, M. (CoI), Scanlon, W. (CoI) & Sezer, S. (CoI)
01/08/2009 → 30/06/2014
Project: Research

Cite this

@conference{d3400088a1304eab98289430b3c6984e,

title = "Detecting Anomalies in Graphs with Numeric Labels",

abstract = "This paper presents Yagada, an algorithm to search labelled graphs for anomalies using both structural data and numeric attributes. Yagada is explained using several security-related examples and validated with experiments on a physical Access Control database. Quantitative analysis shows that in the upper range of anomaly thresholds, Yagada detects twice as many anomalies as the best-performing numeric discretization algorithm. Qualitative evaluation shows that the detected anomalies are meaningful, representing a com- bination of structural irregularities and numerical outliers.",

author = "Michael Davis and Weiru Liu and Paul Miller and George Redpath",

note = "ISSN: 978-1-4503-0717-8; 20th ACM Conference on Information and Knowledge Management, CIKM 2011 ; Conference date: 24-10-2011 Through 28-10-2011",

year = "2011",

month = oct,

doi = "10.1145/2063576.2063749",

language = "English",

pages = "1197--1202",

}

TY - CONF

T1 - Detecting Anomalies in Graphs with Numeric Labels

AU - Davis, Michael

AU - Liu, Weiru

AU - Miller, Paul

AU - Redpath, George

N1 - ISSN: 978-1-4503-0717-8

PY - 2011/10

Y1 - 2011/10

N2 - This paper presents Yagada, an algorithm to search labelled graphs for anomalies using both structural data and numeric attributes. Yagada is explained using several security-related examples and validated with experiments on a physical Access Control database. Quantitative analysis shows that in the upper range of anomaly thresholds, Yagada detects twice as many anomalies as the best-performing numeric discretization algorithm. Qualitative evaluation shows that the detected anomalies are meaningful, representing a com- bination of structural irregularities and numerical outliers.

AB - This paper presents Yagada, an algorithm to search labelled graphs for anomalies using both structural data and numeric attributes. Yagada is explained using several security-related examples and validated with experiments on a physical Access Control database. Quantitative analysis shows that in the upper range of anomaly thresholds, Yagada detects twice as many anomalies as the best-performing numeric discretization algorithm. Qualitative evaluation shows that the detected anomalies are meaningful, representing a com- bination of structural irregularities and numerical outliers.

U2 - 10.1145/2063576.2063749

DO - 10.1145/2063576.2063749

M3 - Paper

SP - 1197

EP - 1202

T2 - 20th ACM Conference on Information and Knowledge Management

Y2 - 24 October 2011 through 28 October 2011

ER -

Detecting Anomalies in Graphs with Numeric Labels

Abstract

Conference

Bibliographical note

Access to Document

Fingerprint

Projects

R1118ECI: Centre for Secure Information Technologies (CSIT)

Cite this