TY - JOUR
T1 - Novel Unsupervised SPITters Detection Scheme by Automatically Solving Unbalanced Situation
AU - Toyoda, Kentaroh
AU - Park, Mirang
AU - Okazaki, Naonobu
AU - Ohtsuki, Tomoaki
N1 - Publisher Copyright:
© 2013 IEEE.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2017
Y1 - 2017
N2 - Spam over Internet telephony (SPIT) is recognized as a new threat for voice communication services such as voice over Internet protocol (VoIP). Due to the privacy reason, it is desired to detect SPITters (SPIT callers) in a VoIP service without training data. Although a clustering-based unsupervised SPITters detection scheme has been proposed, it does not work well when the SPITters account for a small fraction of the entire caller. In this paper, we propose an unsupervised SPITters detection scheme by adding artificial SPITters data to solve the unbalanced situation. The key contribution is to propose a novel way to automatically decide how much artificial data should be added. We show that classification performance is improved by means of computer simulation with real and artificial call log data sets.
AB - Spam over Internet telephony (SPIT) is recognized as a new threat for voice communication services such as voice over Internet protocol (VoIP). Due to the privacy reason, it is desired to detect SPITters (SPIT callers) in a VoIP service without training data. Although a clustering-based unsupervised SPITters detection scheme has been proposed, it does not work well when the SPITters account for a small fraction of the entire caller. In this paper, we propose an unsupervised SPITters detection scheme by adding artificial SPITters data to solve the unbalanced situation. The key contribution is to propose a novel way to automatically decide how much artificial data should be added. We show that classification performance is improved by means of computer simulation with real and artificial call log data sets.
KW - SPIT (spam over internet telephony)
KW - VoIP (voice over internet protocol)
KW - security
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85028343565&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85028343565&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2016.2642978
DO - 10.1109/ACCESS.2016.2642978
M3 - Article
AN - SCOPUS:85028343565
VL - 5
SP - 6746
EP - 6756
JO - IEEE Access
JF - IEEE Access
SN - 2169-3536
M1 - 7792553
ER -