The metric of bulk repeated call detection

Author

Hu, Nan ; Gengyu We ; Wei, Gengyu ; Yixian Yang

Author_Institution

Key Lab. of Network & Inf. Attack & Defense Technol. of MOE, Beijing Univ. of Posts & Telecommun., Beijing, China

fYear

2010

fDate

26-28 Oct. 2010

Firstpage

1192

Lastpage

1196

Abstract

Spam over Internet Telephony (SPIT) has become a serious issue for VoIP applications. SPIT detection is gaining huge focus in recent years. In this paper, we analyzed SPIT calls encoded using VBR method with the feature of bulk repeated. The chi-square test is used to intuitively verify the similarity among the lengths of VoIP packets which are with the characteristic of bulk repeated. In addition to chi-square test, edit distance is introduced to measure the similarity among VoIP calls which can be aided in bulk repeated call detection. It is empirically inferred that the proposed metric may be as good as possible to detect bulk repeated call.

Keywords

Internet telephony; encoding; unsolicited e-mail; variable rate codes; voice communication; VBR method; VoIP application; VoIP packet; bulk repeated call detection; chisquare test; spam over Internet telephony; Cryptography; Educational institutions; Helium; Industries; Measurement; Privacy; Unsolicited electronic mail; VBR; chi-square test; edit distance; sequence similarity;

fLanguage

English

Publisher

ieee

Conference_Titel

Broadband Network and Multimedia Technology (IC-BNMT), 2010 3rd IEEE International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-6769-3

Type

conf

DOI

10.1109/ICBNMT.2010.5705278

Filename

5705278