Unsupervised clustering-based SPITters detection scheme

Kentaro Toyoda, Iwao Sasase

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

VoIP/SIP is taking place of conventional telephony because of very low call charge but it is also attractive for SPITters who advertise or spread phishing calls toward many callees. Although there exist many feature-based SPIT detection methods, none of them provides the flexibility against multiple features and thus complex threshold settings and training phases cannot be avoided. In this paper, we propose an unsupervised and threshold-free SPITters detection scheme based on a clustering algorithm. Our scheme does not use multiple features directly to trap SPITters but uses them to find the dissimilarity among each caller pair and tries to separate the callers into a SPITters cluster and a legitimate one based on the dissimilarity. By computer simulation, we show that the combination of Random Forests dissimilarity and PAM clustering brings the best classification accuracy and our scheme works well when the SPITters account for more than 20% of the entire caller.

Original languageEnglish
Pages (from-to)81-92
Number of pages12
JournalJournal of Information Processing
Volume23
Issue number1
DOIs
Publication statusPublished - 2015 Jan 15

Fingerprint

Pulse amplitude modulation
Clustering algorithms
Computer simulation

Keywords

  • SPIT
  • VoIP/SIP security

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Unsupervised clustering-based SPITters detection scheme. / Toyoda, Kentaro; Sasase, Iwao.

In: Journal of Information Processing, Vol. 23, No. 1, 15.01.2015, p. 81-92.

Research output: Contribution to journalArticle

@article{b9dbf24d60c641cd8a41da6dd5f8a2eb,
title = "Unsupervised clustering-based SPITters detection scheme",
abstract = "VoIP/SIP is taking place of conventional telephony because of very low call charge but it is also attractive for SPITters who advertise or spread phishing calls toward many callees. Although there exist many feature-based SPIT detection methods, none of them provides the flexibility against multiple features and thus complex threshold settings and training phases cannot be avoided. In this paper, we propose an unsupervised and threshold-free SPITters detection scheme based on a clustering algorithm. Our scheme does not use multiple features directly to trap SPITters but uses them to find the dissimilarity among each caller pair and tries to separate the callers into a SPITters cluster and a legitimate one based on the dissimilarity. By computer simulation, we show that the combination of Random Forests dissimilarity and PAM clustering brings the best classification accuracy and our scheme works well when the SPITters account for more than 20{\%} of the entire caller.",
keywords = "SPIT, VoIP/SIP security",
author = "Kentaro Toyoda and Iwao Sasase",
year = "2015",
month = "1",
day = "15",
doi = "10.2197/ipsjjip.23.81",
language = "English",
volume = "23",
pages = "81--92",
journal = "Journal of Information Processing",
issn = "0387-5806",
publisher = "Information Processing Society of Japan",
number = "1",

}

TY - JOUR

T1 - Unsupervised clustering-based SPITters detection scheme

AU - Toyoda, Kentaro

AU - Sasase, Iwao

PY - 2015/1/15

Y1 - 2015/1/15

N2 - VoIP/SIP is taking place of conventional telephony because of very low call charge but it is also attractive for SPITters who advertise or spread phishing calls toward many callees. Although there exist many feature-based SPIT detection methods, none of them provides the flexibility against multiple features and thus complex threshold settings and training phases cannot be avoided. In this paper, we propose an unsupervised and threshold-free SPITters detection scheme based on a clustering algorithm. Our scheme does not use multiple features directly to trap SPITters but uses them to find the dissimilarity among each caller pair and tries to separate the callers into a SPITters cluster and a legitimate one based on the dissimilarity. By computer simulation, we show that the combination of Random Forests dissimilarity and PAM clustering brings the best classification accuracy and our scheme works well when the SPITters account for more than 20% of the entire caller.

AB - VoIP/SIP is taking place of conventional telephony because of very low call charge but it is also attractive for SPITters who advertise or spread phishing calls toward many callees. Although there exist many feature-based SPIT detection methods, none of them provides the flexibility against multiple features and thus complex threshold settings and training phases cannot be avoided. In this paper, we propose an unsupervised and threshold-free SPITters detection scheme based on a clustering algorithm. Our scheme does not use multiple features directly to trap SPITters but uses them to find the dissimilarity among each caller pair and tries to separate the callers into a SPITters cluster and a legitimate one based on the dissimilarity. By computer simulation, we show that the combination of Random Forests dissimilarity and PAM clustering brings the best classification accuracy and our scheme works well when the SPITters account for more than 20% of the entire caller.

KW - SPIT

KW - VoIP/SIP security

UR - http://www.scopus.com/inward/record.url?scp=84921317636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921317636&partnerID=8YFLogxK

U2 - 10.2197/ipsjjip.23.81

DO - 10.2197/ipsjjip.23.81

M3 - Article

AN - SCOPUS:84921317636

VL - 23

SP - 81

EP - 92

JO - Journal of Information Processing

JF - Journal of Information Processing

SN - 0387-5806

IS - 1

ER -