On hit inflation techniques and detection in streams of web advertising networks

Ahmed Metwally, Divyakant Agrawal, Amr El Abbadi, Zheng Qi

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

24 Citations (Scopus)

Abstract

Click fraud is jeopardizing the industry of Internet advertising. Internet advertising is crucial for the thriving of the entire Internet, since it allows producers to advertise their products, and hence contributes to the well being of e-commerce. Moreover, advertising supports the intellectual value of the Internet by covering the running expenses of the content publishers' sites. Some publishers are dishonest, and use automation to generate traffic to defraud the advertisers. Similarly, some advertisers automate clicks on the advertisements of their competitors to deplete their competitors ' advertising budgets. In this paper, we describe the advertising network model, and discuss the issue of fraud that is an integral problem in such setting. We propose using online algorithms on aggregate data to accurately and proactively detect automated traffic, preserve surfers' privacy, while not altering the industry model. We provide a complete classification of the hit inflation techniques; and devise stream analysis techniques that detect a variety of fraud attacks. We abstract detecting the fraud attacks of some classes as theoretical stream analysis problems that we bring to the data management research community as open problems. A framework is outlined for deploying the proposed detection algorithms on a generic architecture. We conclude by some successful preliminary findings of our attempt to detect fraud on a real network.

Original languageEnglish
Title of host publicationProceedings - International Conference on Distributed Computing Systems
DOIs
Publication statusPublished - 8 Oct 2007
Externally publishedYes
Event27th International Conference on Distributed Computing Systems, ICDCS'07 - Toronto, ON, Canada
Duration: 25 Jun 200727 Jun 2007

Other

Other27th International Conference on Distributed Computing Systems, ICDCS'07
CountryCanada
CityToronto, ON
Period25/6/0727/6/07

Fingerprint

Marketing
Internet
Information management
Industry
Automation

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Metwally, A., Agrawal, D., El Abbadi, A., & Qi, Z. (2007). On hit inflation techniques and detection in streams of web advertising networks. In Proceedings - International Conference on Distributed Computing Systems [4268205] https://doi.org/10.1109/ICDCS.2007.124

On hit inflation techniques and detection in streams of web advertising networks. / Metwally, Ahmed; Agrawal, Divyakant; El Abbadi, Amr; Qi, Zheng.

Proceedings - International Conference on Distributed Computing Systems. 2007. 4268205.

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

Metwally, A, Agrawal, D, El Abbadi, A & Qi, Z 2007, On hit inflation techniques and detection in streams of web advertising networks. in Proceedings - International Conference on Distributed Computing Systems., 4268205, 27th International Conference on Distributed Computing Systems, ICDCS'07, Toronto, ON, Canada, 25/6/07. https://doi.org/10.1109/ICDCS.2007.124
Metwally A, Agrawal D, El Abbadi A, Qi Z. On hit inflation techniques and detection in streams of web advertising networks. In Proceedings - International Conference on Distributed Computing Systems. 2007. 4268205 https://doi.org/10.1109/ICDCS.2007.124
Metwally, Ahmed ; Agrawal, Divyakant ; El Abbadi, Amr ; Qi, Zheng. / On hit inflation techniques and detection in streams of web advertising networks. Proceedings - International Conference on Distributed Computing Systems. 2007.
@inproceedings{3d644e928eb34c2880d2a9496ecd0df0,
title = "On hit inflation techniques and detection in streams of web advertising networks",
abstract = "Click fraud is jeopardizing the industry of Internet advertising. Internet advertising is crucial for the thriving of the entire Internet, since it allows producers to advertise their products, and hence contributes to the well being of e-commerce. Moreover, advertising supports the intellectual value of the Internet by covering the running expenses of the content publishers' sites. Some publishers are dishonest, and use automation to generate traffic to defraud the advertisers. Similarly, some advertisers automate clicks on the advertisements of their competitors to deplete their competitors ' advertising budgets. In this paper, we describe the advertising network model, and discuss the issue of fraud that is an integral problem in such setting. We propose using online algorithms on aggregate data to accurately and proactively detect automated traffic, preserve surfers' privacy, while not altering the industry model. We provide a complete classification of the hit inflation techniques; and devise stream analysis techniques that detect a variety of fraud attacks. We abstract detecting the fraud attacks of some classes as theoretical stream analysis problems that we bring to the data management research community as open problems. A framework is outlined for deploying the proposed detection algorithms on a generic architecture. We conclude by some successful preliminary findings of our attempt to detect fraud on a real network.",
author = "Ahmed Metwally and Divyakant Agrawal and {El Abbadi}, Amr and Zheng Qi",
year = "2007",
month = "10",
day = "8",
doi = "10.1109/ICDCS.2007.124",
language = "English",
isbn = "0769528376",
booktitle = "Proceedings - International Conference on Distributed Computing Systems",

}

TY - GEN

T1 - On hit inflation techniques and detection in streams of web advertising networks

AU - Metwally, Ahmed

AU - Agrawal, Divyakant

AU - El Abbadi, Amr

AU - Qi, Zheng

PY - 2007/10/8

Y1 - 2007/10/8

N2 - Click fraud is jeopardizing the industry of Internet advertising. Internet advertising is crucial for the thriving of the entire Internet, since it allows producers to advertise their products, and hence contributes to the well being of e-commerce. Moreover, advertising supports the intellectual value of the Internet by covering the running expenses of the content publishers' sites. Some publishers are dishonest, and use automation to generate traffic to defraud the advertisers. Similarly, some advertisers automate clicks on the advertisements of their competitors to deplete their competitors ' advertising budgets. In this paper, we describe the advertising network model, and discuss the issue of fraud that is an integral problem in such setting. We propose using online algorithms on aggregate data to accurately and proactively detect automated traffic, preserve surfers' privacy, while not altering the industry model. We provide a complete classification of the hit inflation techniques; and devise stream analysis techniques that detect a variety of fraud attacks. We abstract detecting the fraud attacks of some classes as theoretical stream analysis problems that we bring to the data management research community as open problems. A framework is outlined for deploying the proposed detection algorithms on a generic architecture. We conclude by some successful preliminary findings of our attempt to detect fraud on a real network.

AB - Click fraud is jeopardizing the industry of Internet advertising. Internet advertising is crucial for the thriving of the entire Internet, since it allows producers to advertise their products, and hence contributes to the well being of e-commerce. Moreover, advertising supports the intellectual value of the Internet by covering the running expenses of the content publishers' sites. Some publishers are dishonest, and use automation to generate traffic to defraud the advertisers. Similarly, some advertisers automate clicks on the advertisements of their competitors to deplete their competitors ' advertising budgets. In this paper, we describe the advertising network model, and discuss the issue of fraud that is an integral problem in such setting. We propose using online algorithms on aggregate data to accurately and proactively detect automated traffic, preserve surfers' privacy, while not altering the industry model. We provide a complete classification of the hit inflation techniques; and devise stream analysis techniques that detect a variety of fraud attacks. We abstract detecting the fraud attacks of some classes as theoretical stream analysis problems that we bring to the data management research community as open problems. A framework is outlined for deploying the proposed detection algorithms on a generic architecture. We conclude by some successful preliminary findings of our attempt to detect fraud on a real network.

UR - http://www.scopus.com/inward/record.url?scp=34848907439&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34848907439&partnerID=8YFLogxK

U2 - 10.1109/ICDCS.2007.124

DO - 10.1109/ICDCS.2007.124

M3 - Conference contribution

SN - 0769528376

SN - 9780769528373

BT - Proceedings - International Conference on Distributed Computing Systems

ER -