2016
DOI: 10.1002/dac.3255
|View full text |Cite
|
Sign up to set email alerts
|

Detection and prevention of spam over Internet telephony in Voice over Internet Protocol networks using Markov chain with incremental SVM

Abstract: This paper is mainly focused on the detection and prevention of the spammers such as telemarketing callers in Voice over Internet Protocol networks. The existing spam over Internet telephony (SPIT) detection mechanisms use call characteristics features such as reputation rate, call rejection rate, and user feedback that might increase the computation overhead and communication overhead. In this paper, a 2-tier model is proposed and implemented for detecting, preventing, and mitigating SPIT callers. The 2-tier … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(3 citation statements)
references
References 33 publications
0
3
0
Order By: Relevance
“…In [16], a Hidden Markov Model was used to detect human and computer VoIP spammers in the Voice over IP protocol. In order to estimate spammer activity, the model is able to incorporate spammer behaviour from several sources into one model.…”
Section: Related Workmentioning
confidence: 99%
“…In [16], a Hidden Markov Model was used to detect human and computer VoIP spammers in the Voice over IP protocol. In order to estimate spammer activity, the model is able to incorporate spammer behaviour from several sources into one model.…”
Section: Related Workmentioning
confidence: 99%
“…Vennila et al [29] introduced two phases model; a SVM classifier to classify the traffic into VoIP and non-VoIP, and an entropy model to classify the VoIP traffic into flooding and non-flooding. Later, in [30] they proposed another two phases model to detect SPIT callers, which used Markov Chain, and incremental SVM classifier.…”
Section: Related Workmentioning
confidence: 99%
“…These solutions operate independently as the standalone systems, and can be grouped into several classes: black-list or white-list based systems [12][13][14], systems analyzing the social behavior and reputation of the caller [15][16][17][18][19][20][21][22][23][24], authenticating the caller by challenging him in the form of CAPTCHA and Turing test [25][26][27]8], imposing extra cost on the caller if he is flagged as unwanted [28] by recipients of call, systems processing speech content [29][30][31][32], analyzing the linguistics from the speech streams [33,34], and statistical systems that analyzes the flow of packets during the call setup phase [35,36] or analyze caller's behavior from the logged CDRs [37,38]. A single standalone SPIT solution can also be employed by combining many individual systems in the form of a collaborative multistage system [28,[39][40][41][42]. Recently, new detection systems have been proposed to fight against the unwanted callers.…”
Section: Standalone Anti-spit Systemsmentioning
confidence: 99%