Computing trusted authority scores in peer-to-peer web search networks

Josiane Xavier Parreira, Debora Donato, Carlos Castillo, Gerhard Weikum

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

9 Citations (Scopus)

Abstract

Peer-to-peer (P2P) networks have received great attention for sharing and searching information in large user communities. The open and anonymous nature of P2P networks is one of its main strengths, but it also opens doors to manipulation of the information and of the quality ratings. In our previous work (J. X. Parreira, D. Donato, S. Michel and G. Weikum in VLDB 2006) we presented the JXP algorithm for distributed computing PageRank scores for information units (Web pages, sites, peers, social groups, etc.) within a link- or endorsement-based graph structure. The algorithm builds on local authority computations and bilateral peer meetings with exchanges of small data structures that are relevant for gradually learning about global properties and eventually converging towards global authority rankings. In the current paper we address the important issue of cheating peers that attempt to distort the global authority values, by providing manipulated data during the peer meetings. Our approach to this problem enhances JXP with statistical techniques for detecting suspicious behavior. Our method, coined Trust JXP, is again completely decentralized, and we demonstrate its viability and robustness in experiments with real Web data.

Original languageEnglish
Title of host publicationACM International Conference Proceeding Series
Pages73-80
Number of pages8
Volume215
DOIs
Publication statusPublished - 31 Oct 2007
Externally publishedYes
EventAIRWeb 2007 - 3rd International Workshop on Adversarial Information Retrieval on the Web - Banff, AB, Canada
Duration: 8 May 20078 May 2007

Other

OtherAIRWeb 2007 - 3rd International Workshop on Adversarial Information Retrieval on the Web
CountryCanada
CityBanff, AB
Period8/5/078/5/07

Fingerprint

Peer to peer networks
Distributed computer systems
Data structures
Websites
Experiments
Trusted computing

Keywords

  • Decentralized PageRank
  • P2P networks
  • Trust

ASJC Scopus subject areas

  • Human-Computer Interaction

Cite this

Parreira, J. X., Donato, D., Castillo, C., & Weikum, G. (2007). Computing trusted authority scores in peer-to-peer web search networks. In ACM International Conference Proceeding Series (Vol. 215, pp. 73-80) https://doi.org/10.1145/1244408.1244422

Computing trusted authority scores in peer-to-peer web search networks. / Parreira, Josiane Xavier; Donato, Debora; Castillo, Carlos; Weikum, Gerhard.

ACM International Conference Proceeding Series. Vol. 215 2007. p. 73-80.

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

Parreira, JX, Donato, D, Castillo, C & Weikum, G 2007, Computing trusted authority scores in peer-to-peer web search networks. in ACM International Conference Proceeding Series. vol. 215, pp. 73-80, AIRWeb 2007 - 3rd International Workshop on Adversarial Information Retrieval on the Web, Banff, AB, Canada, 8/5/07. https://doi.org/10.1145/1244408.1244422
Parreira JX, Donato D, Castillo C, Weikum G. Computing trusted authority scores in peer-to-peer web search networks. In ACM International Conference Proceeding Series. Vol. 215. 2007. p. 73-80 https://doi.org/10.1145/1244408.1244422
Parreira, Josiane Xavier ; Donato, Debora ; Castillo, Carlos ; Weikum, Gerhard. / Computing trusted authority scores in peer-to-peer web search networks. ACM International Conference Proceeding Series. Vol. 215 2007. pp. 73-80
@inproceedings{3ee686ca02fd45459c34975f9467903c,
title = "Computing trusted authority scores in peer-to-peer web search networks",
abstract = "Peer-to-peer (P2P) networks have received great attention for sharing and searching information in large user communities. The open and anonymous nature of P2P networks is one of its main strengths, but it also opens doors to manipulation of the information and of the quality ratings. In our previous work (J. X. Parreira, D. Donato, S. Michel and G. Weikum in VLDB 2006) we presented the JXP algorithm for distributed computing PageRank scores for information units (Web pages, sites, peers, social groups, etc.) within a link- or endorsement-based graph structure. The algorithm builds on local authority computations and bilateral peer meetings with exchanges of small data structures that are relevant for gradually learning about global properties and eventually converging towards global authority rankings. In the current paper we address the important issue of cheating peers that attempt to distort the global authority values, by providing manipulated data during the peer meetings. Our approach to this problem enhances JXP with statistical techniques for detecting suspicious behavior. Our method, coined Trust JXP, is again completely decentralized, and we demonstrate its viability and robustness in experiments with real Web data.",
keywords = "Decentralized PageRank, P2P networks, Trust",
author = "Parreira, {Josiane Xavier} and Debora Donato and Carlos Castillo and Gerhard Weikum",
year = "2007",
month = "10",
day = "31",
doi = "10.1145/1244408.1244422",
language = "English",
isbn = "1595937323",
volume = "215",
pages = "73--80",
booktitle = "ACM International Conference Proceeding Series",

}

TY - GEN

T1 - Computing trusted authority scores in peer-to-peer web search networks

AU - Parreira, Josiane Xavier

AU - Donato, Debora

AU - Castillo, Carlos

AU - Weikum, Gerhard

PY - 2007/10/31

Y1 - 2007/10/31

N2 - Peer-to-peer (P2P) networks have received great attention for sharing and searching information in large user communities. The open and anonymous nature of P2P networks is one of its main strengths, but it also opens doors to manipulation of the information and of the quality ratings. In our previous work (J. X. Parreira, D. Donato, S. Michel and G. Weikum in VLDB 2006) we presented the JXP algorithm for distributed computing PageRank scores for information units (Web pages, sites, peers, social groups, etc.) within a link- or endorsement-based graph structure. The algorithm builds on local authority computations and bilateral peer meetings with exchanges of small data structures that are relevant for gradually learning about global properties and eventually converging towards global authority rankings. In the current paper we address the important issue of cheating peers that attempt to distort the global authority values, by providing manipulated data during the peer meetings. Our approach to this problem enhances JXP with statistical techniques for detecting suspicious behavior. Our method, coined Trust JXP, is again completely decentralized, and we demonstrate its viability and robustness in experiments with real Web data.

AB - Peer-to-peer (P2P) networks have received great attention for sharing and searching information in large user communities. The open and anonymous nature of P2P networks is one of its main strengths, but it also opens doors to manipulation of the information and of the quality ratings. In our previous work (J. X. Parreira, D. Donato, S. Michel and G. Weikum in VLDB 2006) we presented the JXP algorithm for distributed computing PageRank scores for information units (Web pages, sites, peers, social groups, etc.) within a link- or endorsement-based graph structure. The algorithm builds on local authority computations and bilateral peer meetings with exchanges of small data structures that are relevant for gradually learning about global properties and eventually converging towards global authority rankings. In the current paper we address the important issue of cheating peers that attempt to distort the global authority values, by providing manipulated data during the peer meetings. Our approach to this problem enhances JXP with statistical techniques for detecting suspicious behavior. Our method, coined Trust JXP, is again completely decentralized, and we demonstrate its viability and robustness in experiments with real Web data.

KW - Decentralized PageRank

KW - P2P networks

KW - Trust

UR - http://www.scopus.com/inward/record.url?scp=35548930306&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35548930306&partnerID=8YFLogxK

U2 - 10.1145/1244408.1244422

DO - 10.1145/1244408.1244422

M3 - Conference contribution

SN - 1595937323

SN - 9781595937322

VL - 215

SP - 73

EP - 80

BT - ACM International Conference Proceeding Series

ER -