Email is an increasingly important and ubiquitous means of communication, both facilitating contact between private individuals and enabling rises in the productivity of organizations. However the relentless rise of automatic unauthorized emails, a.k.a. spam is eroding away much of the attractiveness of email communication. Most of the attention dedicated to date to spam detection has focused on the content of the emails or on the addresses or domains associated with spam senders. Although methods based on these - easily changeable - identifiers work reasonably well they miss on the fundamental nature of spam as an opportunistic relationship, very different from the normal mutual relations between senders and recipients of legitimate email. Here we present a comprehensive graph theoretical analysis of email traffic that captures these properties quantitatively. We identify several simple metrics that serve both to distinguish between spam and legitimate email and to provide a statistical basis for models of spam traffic.

@misc{gomes-2005, author = {Gomes, Luiz H. and Almeida, Rodrigo B. and Bettencourt, Luis M. A. and Almeida, Virgilio and Almeida, Jussara M.}, title = {Comparative Graph Theoretical Characterization of Networks of Spam and Legitimate Email}, year = {2005}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:physics/0504025}, keywords = {email, graph, network, spam}, abstract = {Email is an increasingly important and ubiquitous means of communication, both facilitating contact between private individuals and enabling rises in the productivity of organizations. However the relentless rise of automatic unauthorized emails, a.k.a. spam is eroding away much of the attractiveness of email communication. Most of the attention dedicated to date to spam detection has focused on the content of the emails or on the addresses or domains associated with spam senders. Although methods based on these - easily changeable - identifiers work reasonably well they miss on the fundamental nature of spam as an opportunistic relationship, very different from the normal mutual relations between senders and recipients of legitimate email. Here we present a comprehensive graph theoretical analysis of email traffic that captures these properties quantitatively. We identify several simple metrics that serve both to distinguish between spam and legitimate email and to provide a statistical basis for models of spam traffic.} }

%0 = misc %A = Gomes, Luiz H. and Almeida, Rodrigo B. and Bettencourt, Luis M. A. and Almeida, Virgilio and Almeida, Jussara M. %B = } %C = %D = 2005 %I = %T = Comparative Graph Theoretical Characterization of Networks of Spam and Legitimate Email} %U = http://www.citebase.org/abstract?id=oai:arXiv.org:physics/0504025

@inproceedings{conf/ceas/KongBRSR05, author = {Kong, Joseph S. and Boykin, P. Oscar and Rezaei, Behnam Attaran and Sarshar, Nima and Roychowdhury, Vwani P.}, title = {Scalable and Reliable Collaborative Spam Filters: Harnessing the Global Social Email Networks.}, booktitle = {CEAS}, year = {2005}, url = {http://dblp.uni-trier.de/db/conf/ceas/ceas2005.html#KongBRSR05}, keywords = {email, network, social, spam} }

%0 = inproceedings %A = Kong, Joseph S. and Boykin, P. Oscar and Rezaei, Behnam Attaran and Sarshar, Nima and Roychowdhury, Vwani P. %B = CEAS %D = 2005 %T = Scalable and Reliable Collaborative Spam Filters: Harnessing the Global Social Email Networks. %U = http://dblp.uni-trier.de/db/conf/ceas/ceas2005.html#KongBRSR05

@misc{golbeck04reputation, author = {Golbeck, J. and Hendler, J.}, title = {Reputation Network Analysis for Email Filtering}, year = {2004}, url = {citeseer.ist.psu.edu/golbeck04reputation.html}, keywords = {email, network, spam} }

%0 = misc %A = Golbeck, J. and Hendler, J. %B = } %C = %D = 2004 %I = %T = Reputation Network Analysis for Email Filtering} %U = citeseer.ist.psu.edu/golbeck04reputation.html

@inproceedings{conf/vldb/GyongyiGP04, author = {Gyöngyi, Zoltán and Garcia-Molina, Hector and Pedersen, Jan}, title = {Combating Web Spam with TrustRank.}, booktitle = {VLDB}, year = {2004}, pages = {576-587}, url = {http://dblp.uni-trier.de/db/conf/vldb/vldb2004.html#GyongyiGP04}, keywords = {network, rank, search, social, spam, summerschool, trust, web} }

%0 = inproceedings %A = Gyöngyi, Zoltán and Garcia-Molina, Hector and Pedersen, Jan %B = VLDB %D = 2004 %T = Combating Web Spam with TrustRank. %U = http://dblp.uni-trier.de/db/conf/vldb/vldb2004.html#GyongyiGP04