Exploring anti-spam models in large scale VoIP systems

Pushkar Patankar, Gunwoo Nam, George Kesidis, Chitaranjan Das

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

Although the problem of spam detection in email is well understood and has been extensively researched, a significant portion of emails today are spam. A most widely used method to detect spam involves content filtering, where the spam detector scans the received email for keywords. However, the same approach cannot be applied to detect Voice over IP (VoIP) spam, since a call has to be categorized as a legitimate or a spam (each to a degree with a certain reliability) before the connection is established. Also, spammers over IP can potentially generate orders of magnitude more spam volume, at far less cost, and with greater anonymity than telemarketers using the Public Switch Telephone Network (PSTN). The spam problem in VoIP is further compounded by the absence of a do-not-call-list, which has been the main reason for the reduction of spam calls in PSTN. Thus, the spam issue for VoIP is as important as those pertaining to quality-of-service (QoS) of the voice traffic itself. To this end, we propose two different anti-spam frameworks for large scale VoIP systems. The first one is a centralized SIP-based spam detection framework that relies on SIP messages during the call establishment phase to identify spam calls, and the second one is a distributed referral social network model, where a user is assigned a reputation score by its neighbors. Based on the reputation, a callee can decide either to accept or decline a call. Our simulation results indicate that the referral model can provide better anti-spam capabilities by isolating a spammer faster than the SIP based approach, and can also correctly identify spam calls over 98% of time.

Original languageEnglish (US)
Title of host publicationProceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008
Pages85-92
Number of pages8
DOIs
StatePublished - Sep 22 2008
Event28th International Conference on Distributed Computing Systems, ICDCS 2008 - Beijing, China
Duration: Jul 17 2008Jul 20 2008

Other

Other28th International Conference on Distributed Computing Systems, ICDCS 2008
CountryChina
CityBeijing
Period7/17/087/20/08

Fingerprint

Electronic mail
Telephone
Switches
Telecommunication traffic
Quality of service
Detectors
Costs

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Software

Cite this

Patankar, P., Nam, G., Kesidis, G., & Das, C. (2008). Exploring anti-spam models in large scale VoIP systems. In Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008 (pp. 85-92). [4595872] https://doi.org/10.1109/ICDCS.2008.71
Patankar, Pushkar ; Nam, Gunwoo ; Kesidis, George ; Das, Chitaranjan. / Exploring anti-spam models in large scale VoIP systems. Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008. 2008. pp. 85-92
@inproceedings{253128eef53e417683dc4fac39f6542c,
title = "Exploring anti-spam models in large scale VoIP systems",
abstract = "Although the problem of spam detection in email is well understood and has been extensively researched, a significant portion of emails today are spam. A most widely used method to detect spam involves content filtering, where the spam detector scans the received email for keywords. However, the same approach cannot be applied to detect Voice over IP (VoIP) spam, since a call has to be categorized as a legitimate or a spam (each to a degree with a certain reliability) before the connection is established. Also, spammers over IP can potentially generate orders of magnitude more spam volume, at far less cost, and with greater anonymity than telemarketers using the Public Switch Telephone Network (PSTN). The spam problem in VoIP is further compounded by the absence of a do-not-call-list, which has been the main reason for the reduction of spam calls in PSTN. Thus, the spam issue for VoIP is as important as those pertaining to quality-of-service (QoS) of the voice traffic itself. To this end, we propose two different anti-spam frameworks for large scale VoIP systems. The first one is a centralized SIP-based spam detection framework that relies on SIP messages during the call establishment phase to identify spam calls, and the second one is a distributed referral social network model, where a user is assigned a reputation score by its neighbors. Based on the reputation, a callee can decide either to accept or decline a call. Our simulation results indicate that the referral model can provide better anti-spam capabilities by isolating a spammer faster than the SIP based approach, and can also correctly identify spam calls over 98{\%} of time.",
author = "Pushkar Patankar and Gunwoo Nam and George Kesidis and Chitaranjan Das",
year = "2008",
month = "9",
day = "22",
doi = "10.1109/ICDCS.2008.71",
language = "English (US)",
isbn = "9780769531724",
pages = "85--92",
booktitle = "Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008",

}

Patankar, P, Nam, G, Kesidis, G & Das, C 2008, Exploring anti-spam models in large scale VoIP systems. in Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008., 4595872, pp. 85-92, 28th International Conference on Distributed Computing Systems, ICDCS 2008, Beijing, China, 7/17/08. https://doi.org/10.1109/ICDCS.2008.71

Exploring anti-spam models in large scale VoIP systems. / Patankar, Pushkar; Nam, Gunwoo; Kesidis, George; Das, Chitaranjan.

Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008. 2008. p. 85-92 4595872.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Exploring anti-spam models in large scale VoIP systems

AU - Patankar, Pushkar

AU - Nam, Gunwoo

AU - Kesidis, George

AU - Das, Chitaranjan

PY - 2008/9/22

Y1 - 2008/9/22

N2 - Although the problem of spam detection in email is well understood and has been extensively researched, a significant portion of emails today are spam. A most widely used method to detect spam involves content filtering, where the spam detector scans the received email for keywords. However, the same approach cannot be applied to detect Voice over IP (VoIP) spam, since a call has to be categorized as a legitimate or a spam (each to a degree with a certain reliability) before the connection is established. Also, spammers over IP can potentially generate orders of magnitude more spam volume, at far less cost, and with greater anonymity than telemarketers using the Public Switch Telephone Network (PSTN). The spam problem in VoIP is further compounded by the absence of a do-not-call-list, which has been the main reason for the reduction of spam calls in PSTN. Thus, the spam issue for VoIP is as important as those pertaining to quality-of-service (QoS) of the voice traffic itself. To this end, we propose two different anti-spam frameworks for large scale VoIP systems. The first one is a centralized SIP-based spam detection framework that relies on SIP messages during the call establishment phase to identify spam calls, and the second one is a distributed referral social network model, where a user is assigned a reputation score by its neighbors. Based on the reputation, a callee can decide either to accept or decline a call. Our simulation results indicate that the referral model can provide better anti-spam capabilities by isolating a spammer faster than the SIP based approach, and can also correctly identify spam calls over 98% of time.

AB - Although the problem of spam detection in email is well understood and has been extensively researched, a significant portion of emails today are spam. A most widely used method to detect spam involves content filtering, where the spam detector scans the received email for keywords. However, the same approach cannot be applied to detect Voice over IP (VoIP) spam, since a call has to be categorized as a legitimate or a spam (each to a degree with a certain reliability) before the connection is established. Also, spammers over IP can potentially generate orders of magnitude more spam volume, at far less cost, and with greater anonymity than telemarketers using the Public Switch Telephone Network (PSTN). The spam problem in VoIP is further compounded by the absence of a do-not-call-list, which has been the main reason for the reduction of spam calls in PSTN. Thus, the spam issue for VoIP is as important as those pertaining to quality-of-service (QoS) of the voice traffic itself. To this end, we propose two different anti-spam frameworks for large scale VoIP systems. The first one is a centralized SIP-based spam detection framework that relies on SIP messages during the call establishment phase to identify spam calls, and the second one is a distributed referral social network model, where a user is assigned a reputation score by its neighbors. Based on the reputation, a callee can decide either to accept or decline a call. Our simulation results indicate that the referral model can provide better anti-spam capabilities by isolating a spammer faster than the SIP based approach, and can also correctly identify spam calls over 98% of time.

UR - http://www.scopus.com/inward/record.url?scp=51849143096&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51849143096&partnerID=8YFLogxK

U2 - 10.1109/ICDCS.2008.71

DO - 10.1109/ICDCS.2008.71

M3 - Conference contribution

SN - 9780769531724

SP - 85

EP - 92

BT - Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008

ER -

Patankar P, Nam G, Kesidis G, Das C. Exploring anti-spam models in large scale VoIP systems. In Proceedings - The 28th International Conference on Distributed Computing Systems, ICDCS 2008. 2008. p. 85-92. 4595872 https://doi.org/10.1109/ICDCS.2008.71