\Sort{ Mode{off} } \ Sort{ Mode{on} Collation{mixed} SortTypeOrder{key,name} NameOrder{ascending} Key{_none} KeyOrder{ascending,nulls first} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % % % % % A Bibliography on Machine Learning for Spam Detection % % % % compiled and maintained by % % % % Jose Maria Gomez Hidalgo % % Universidad Europea de Madrid % % Villaviciosa de Odon 28670, Madrid, Spain % % http://www.esi.uem.es/~jmgomez/ % % jmgomez AT uem DOT es % % % % % % This is a bibliography, in BibTeX format, on machine learning % % methods for spam (unsolicited bulk or commercial) mail detection. % % % % This bibliography resides at % % http://www.esi.uem.es/~jmgomez/spam/MLSpamBibliography.bib % % Everyone is welcome to download it as a whole and distribute it, % % provided that it is distributed untouched. % % % % Everyone is also welcome to let me know either additional % % references or corrections and additions (e.g. URLs, where % % they are not already present) to the existing ones. % % In general, only references specific to machine learning methods % % for spam email detection are considered pertinent to this % % bibliography. % % % % Concerning URLs from which to download on-line copies of the % % papers, where possible I have included URLs with unrestricted % % access (e.g. home pages of authors). When such URLs were not % % available, sometimes a URL with restricted access (e.g. the % % ACM Digital Library or the IEEE Computing Society Digital % % Library, which are accessible to subscribers only) is indicated. % % When this is the case, if you know of a URL with unrestricted access % % from which the paper is also available, please let me know and I % % will substitute the link. % % % % This disclaimer is adapted from the ATC bibliography by Fabrizio % % Sebastiani. % % % %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @INPROCEEDINGS{Abadi03a, author = {M. Abadi and A. Birrell and M. Burrows and F. Dabek and T. Wobber}, month = {December}, year = 2003, title = {Bankable Postage for Network Services}, booktitle = {Proceedings of the 8th Asian Computing Science Conference}, note = {Available: \url{http://research.microsoft.com/research/sv/sv-pubs/TicketServer.pdf}}, address = {Mumbai, India}, keywords = {POSTAGE}, url = {http://research.microsoft.com/research/sv/sv-pubs/TicketServer.pdf} } @INPROCEEDINGS{Abadi03b, author = {M. Abadi and M. Burrows and M. Manasse and T. Wobber}, month = {February}, year = 2003, title = {Moderately Hard, Memory-Bound Functions}, booktitle = {Proceedings of the 10th Annual Network and Distributed System Security Symposium}, note = {Available: \url{http://research.microsoft.com/research/sv/sv-pubs/memory-final-ndss.pdf}}, keywords = {POSTAGE}, url = { http://research.microsoft.com/research/sv/sv-pubs/memory-final-ndss.pdf} } @INPROCEEDINGS{Ahmed04, author = {Shabbir Ahmed and Farzana Mithun}, year = 2004, title = {Word Stemming to Enhance Spam Filtering}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/167.pdf}}, keywords = {BAYESIAN}, url = {http://www.ceas.cc/papers-2004/167.pdf} } @INPROCEEDINGS{Androutsopoulos00a, author = {I. Androutsopoulos and J. Koutsias and K.V. Chandrinos and G. Paliouras and C.D. Spyropoulos}, editor = {G. Potamias and V. Moustakis and M.n van Someren}, year = 2000, title = {An Evaluation of Naive Bayesian Anti-Spam Filtering}, booktitle = {Proceedings of the Workshop on Machine Learning in the New Information Age, 11th European Conference on Machine Learning (ECML 2000)}, pages = {9--17}, note = {Available: \url{http://arXiv.org/abs/cs.CL/0006013}}, address = {Barcelona, Spain}, keywords = {BAYESIAN}, url = {http://arXiv.org/abs/cs.CL/0006013} } @INPROCEEDINGS{Androutsopoulos00b, author = {I. Androutsopoulos and G. Paliouras and V. Karkaletsis and G. Sakkis and C.D. Spyropoulos and P. Stamatopoulos}, editor = {H. Zaragoza and P. Gallinari and and M. Rajman}, year = 2000, title = {Learning to Filter Spam E-Mail: A Comparison of a Naive Bayesian and a Memory-Based Approach}, booktitle = {Proceedings of the Workshop on Machine Learning and Textual Information Access, 4th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2000)}, pages = {1--13}, note = {Available: \url{http://arXiv.org/abs/cs/0009009}}, address = {Lyon, France}, keywords = {BAYESIAN}, url = {http://arXiv.org/abs/cs/0009009} } @INPROCEEDINGS{Androutsopoulos00c, author = {Ion Androutsopoulos and John Koutsias and Konstandinos V. Chandrinos and Constantine D. Spyropoulos}, editor = {Nicholas J. Belkin and Peter Ingwersen and Mun-Kew Leong}, year = 2000, title = {An experimental comparison of naive {B}ayesian and keyword-based anti-spam filtering with personal e-mail messages}, booktitle = {Proceedings of SIGIR-00, 23rd ACM International Conference on Research and Development in Information Retrieval}, pages = {160--167}, note = {Available: \url{http://www.acm.org/pubs/articles/proceedings/ir/345508/p160-androutsopoulos/p160-androutsopoulos.pdf}}, publisher = {ACM Press, New York, US}, address = {Athens, GR}, keywords = {BAYESIAN}, url = { http://www.acm.org/pubs/articles/proceedings/ir/345508/p160-androutsopoulos/p160-androutsopoulos.pdf} } @INPROCEEDINGS{Burton03, author = {Brian Burton}, year = 2003, title = {Bayesian Spam Filtering Tweaks}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://spamprobe.sourceforge.net/paper.html}}, keywords = {BAYESIAN}, url = {http://spamprobe.sourceforge.net/paper.html} } @INPROCEEDINGS{Carreras01, author = {Xavier Carreras and Llu{\'{\i}}s M{\'a}rquez}, year = 2001, title = {Boosting Trees for Anti-Spam Email Filtering}, booktitle = {Proceedings of RANLP-2001, 4th International Conference on Recent Advances in Natural Language Processing}, note = {Available: \url{http://www.lsi.upc.es/~carreras/pub/boospam.ps}}, keywords = {BAYESIAN}, url = {http://www.lsi.upc.es/~carreras/pub/boospam.ps} } @INPROCEEDINGS{Clayton04, author = {Richard Clayton}, year = 2004, title = {Stopping Spam by Extrusion Detection}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/172.pdf}}, keywords = {TECHNICAL}, url = {http://www.ceas.cc/papers-2004/172.pdf} } @ARTICLE{Cranor98, author = {L. F. Cranor and B. A. LaMacchia}, year = 1998, title = {Spam!}, journal = {Communications of the ACM}, volume = 41, number = 8, pages = {74--83}, note = {Available: \url{http://lorrie.cranor.org/pubs/spam/spam.html}}, keywords = {GENERAL}, url = {http://lorrie.cranor.org/pubs/spam/spam.html} } @INPROCEEDINGS{Cunningham03, author = {P{\'a}draig Cunningham and Niamh Nowlan and Sarah Jane Delany and Mads Haahr}, month = {June}, year = 2003, title = {A Case-Based Approach to Spam Filtering that Can Track Concept Drift}, booktitle = {The ICCBR'03 Workshop on Long-Lived CBR Systems}, note = {Available: \url{http://www.cs.tcd.ie/publications/tech-reports/reports.03/TCD-CS-2003-16.pdf}}, address = {Trondheim, Norway}, keywords = {COLLABORATIVE}, url = { http://www.cs.tcd.ie/publications/tech-reports/reports.03/TCD-CS-2003-16.pdf} } @INPROCEEDINGS{Dai04, author = {Rui Dai and Kang Li}, year = 2004, title = {Shall We Stop All Unsolicited Email Messages?}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/189.pdf}}, keywords = {POSTAGE}, url = {http://www.ceas.cc/papers-2004/189.pdf} } @INPROCEEDINGS{Drake04, author = {{Christine E.} Drake and {Jonathan J.} Oliver and Eugene J. Koontz}, year = 2004, title = {Anatomy of a Phishing Email}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/114.pdf}}, keywords = {OTHER}, url = {http://www.ceas.cc/papers-2004/114.pdf} } @ARTICLE{Drucker99, author = {Harris Drucker and Vladimir Vapnik and Dongui Wu}, year = 1999, title = {Support Vector Machines for Spam Categorization}, journal = {IEEE Transactions on Neural Networks}, volume = 10, number = 5, pages = {1048--1054}, note = {Available: \url{http://www.monmouth.edu/~drucker/SVM_spam_article_compete.PDF}}, keywords = {BAYESIAN}, url = {http://www.monmouth.edu/~drucker/SVM_spam_article_compete.PDF} } @INPROCEEDINGS{Dwork93, author = {C. Dwork and M. Naor}, year = 1993, title = {Pricing Via Processing or Combatting Junk Mail}, booktitle = {Proceedings of {CRYPTO'92}, Lecture Notes in Computer Science 740}, pages = {137--147}, note = {Available: \url{http://www.wisdom.weizmann.ac.il/%7Enaor/PAPERS/pvp.ps}}, keywords = {POSTAGE}, url = {http://www.wisdom.weizmann.ac.il/%7Enaor/PAPERS/pvp.ps} } @INPROCEEDINGS{Dwork03, author = {C. Dwork and A. Goldberg and M. Naor}, month = {August}, year = 2003, title = {On Memory-Bound Functions for Fighting Spam}, booktitle = {Proceedings of the 23rd Annual International Cryptology Conference {(CRYPTO} 2003)}, note = {Available: \url{http://www.wisdom.weizmann.ac.il/%7Enaor/PAPERS/mem.pdf}}, keywords = {POSTAGE}, url = {http://www.wisdom.weizmann.ac.il/%7Enaor/PAPERS/mem.pdf} } @MISC{Eide03, author = {Kristian Eide}, month = {August}, year = 2003, title = {Winning the War on spam: {C}omparison of Bayesian spam filters}, note = {Available: \url{http://home.dataparty.no/kristian/reviews/bayesian/}}, keywords = {BAYESIAN}, url = {http://home.dataparty.no/kristian/reviews/bayesian/} } @ARTICLE{Fahlman02, author = {{S. E.} Fahlman}, year = 2002, title = {Selling Interrupt Rights: A Way to Control Unwanted Email and Telephone Calls}, journal = {IBM Systems Journal}, volume = 41, number = 4, pages = {759--766}, note = {Available: \url{http://www.research.ibm.com/journal/sj/414/forum.pdf}}, keywords = {POSTAGE}, url = {http://www.research.ibm.com/journal/sj/414/forum.pdf} } @ARTICLE{Fawcett03, author = {Tom Fawcett}, month = {December}, year = 2003, title = {'In Vivo' Spam Filtering: A Challenge Problem for Data Mining}, journal = {KDD Explorations}, volume = 5, number = 2, note = {Available: \url{http://www.hpl.hp.com/personal/Tom_Fawcett/papers/spam-KDDexp.pdf}}, keywords = {BAYESIAN}, url = {http://www.hpl.hp.com/personal/Tom_Fawcett/papers/spam-KDDexp.pdf} } @INPROCEEDINGS{Fetterly04, author = {Dennis Fetterly and Mark Manasse and Marc Najork}, month = {June}, year = 2004, title = {Spam, Damn Spam, and Statistics: Using Statistical Analysis to Locate Spam Web Pages}, booktitle = {Proceedings of the 7th International Workshop on the Web and Databases}, pages = {1--6}, note = {Available: \url{http://research.microsoft.com/~najork/webdb2004.pdf}}, address = {Paris, France}, keywords = {BAYESIAN}, url = {http://research.microsoft.com/~najork/webdb2004.pdf} } @INPROCEEDINGS{Gee03, author = {{Kevin R.} Gee}, year = 2003, title = {Using Latent Semantic Indexing to Filter Spam}, booktitle = {{ACM} Symposium on Applied Computing, Data Mining Track}, pages = {460-464}, note = {Available: \url{http://ranger.uta.edu/~cook/pubs/sac03.ps}}, keywords = {BAYESIAN}, url = {http://ranger.uta.edu/~cook/pubs/sac03.ps} } @INPROCEEDINGS{Golbeck04, author = {Jennifer Golbeck and James Hendler}, year = 2004, title = {Reputation Network Analysis for Email Filtering}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/177.pdf}}, keywords = {COLLABORATIVE}, url = {http://www.ceas.cc/papers-2004/177.pdf} } @INPROCEEDINGS{Gomez00, author = {{Jos{\'e} Mar{\'{\i}}a} G{\'o}mez-Hidalgo and Manuel {Ma{\~n}a-L{\'o}pez} and Enrique {Puertas-Sanz}}, year = 2000, title = {Combining Text and Heuristics for Cost-Sensitive Spam Filtering}, booktitle = {Proceedings of the Fourth Computational Natural Language Learning Workshop, CoNLL-2000}, note = {Available: \url{http://www.esi.uem.es/~jmgomez/papers/conll00.ps}}, publisher = {Association for Computational Linguistics}, address = {Lisbon, Portugal}, keywords = {BAYESIAN}, url = {http://www.esi.uem.es/~jmgomez/papers/conll00.ps} } @INPROCEEDINGS{Gomez02a, author = {{Jos{\'e} Mar{\'{\i}}a} {G{\'o}mez-Hidalgo}}, year = 2002, title = {Evaluating Cost-Sensitive Unsolicited Bulk Email Categorization}, booktitle = {Proceedings of SAC-02, 17th ACM Symposium on Applied Computing}, pages = {615--620}, note = {Available: \url{http://www.esi.uem.es/~jmgomez/papers/report01a.pdf}}, address = {Madrid, ES}, keywords = {BAYESIAN}, url = {http://www.esi.uem.es/~jmgomez/papers/report01a.pdf} } @INPROCEEDINGS{Gomez02b, author = {{Jos{\'e} Mar{\'{\i}}a} G{\'o}mez-Hidalgo and Manuel Ma{\~n}a-L{\'o}pez and Enrique {Puertas-Sanz}}, year = 2002, title = {Evaluating Cost-Sensitive Unsolicited Bulk Email Categorization}, booktitle = {Proceedings of {JADT}-02, 6th International Conference on the Statistical Analysis of Textual Data}, note = {Available: \url{http://www.esi.uem.es/~jmgomez/spam/report01a.pdf}}, address = {Madrid, ES}, keywords = {BAYESIAN}, url = {http://www.esi.uem.es/~jmgomez/spam/report01a.pdf} } @INPROCEEDINGS{Goodman03, author = {Joshua Goodman}, month = {January}, year = 2003, title = {Fighting Spam in the Real World}, booktitle = {Proceedings of the 2003 Spam Conference}, note = {Available: \url{http://www.research.microsoft.com/~joshuago/spamconferenceshort.ppt}}, keywords = {GENERAL}, url = {http://www.research.microsoft.com/~joshuago/spamconferenceshort.ppt} } @INPROCEEDINGS{Goodman04a, author = {Joshua Goodman and Robert Rounthwaite}, month = {May}, year = 2004, title = {Stopping Outgoing Spam}, booktitle = {{ACM} Conference on E-Commerce}, note = {Available: \url{http://research.microsoft.com/~joshuago/outgoingspam-final-submit.pdf}}, keywords = {POSTAGE}, url = { http://research.microsoft.com/~joshuago/outgoingspam-final-submit.pdf} } @ARTICLE{Goodman04b, author = {Joshua Goodman and David Heckerman}, year = 2004, title = {Stopping Spam with Statistics}, journal = {Significance, the Magazine of the Royal Statistical Society}, note = {To apear. Available: \url{http://research.microsoft.com/~joshuago/significance-spam_edited2-times.pdf}}, keywords = {GENERAL}, url = { http://research.microsoft.com/~joshuago/significance-spam_edited2-times.pdf} } @INPROCEEDINGS{Goodman04c, author = {Joshua Goodman}, year = 2004, title = {{IP} Addreses in Email Clients}, booktitle = {Proceedings of The First Conference on Email and Anti-Spam}, note = {Available: \url{http://research.microsoft.com/~joshuago/ipaddressesinclients-final.pdf}}, keywords = {LISTS}, url = { http://research.microsoft.com/~joshuago/ipaddressesinclients-final.pdf} } @INPROCEEDINGS{Graham02, author = {Paul Graham}, year = 2002, title = {A Plan for Spam}, booktitle = {Reprinted in Paul Graham, Hackers and Painters, Big Ideas from the Computer Age, {O’Really}, 2004}, note = {Available: \url{http://www.paulgraham.com/spam.html}}, keywords = {BAYESIAN}, url = {http://www.paulgraham.com/spam.html} } @INPROCEEDINGS{Graham03, author = {Paul Graham}, month = {Jan}, year = 2003, title = {Better Bayesian Filtering}, booktitle = {Proceedings of the 2003 Spam Conference}, note = {Available: \url{http://www.paulgraham.com/better.html}}, howpublished = {Available: \url{http://www.paulgraham.com/better.html}}, keywords = {BAYESIAN}, url = {http://www.paulgraham.com/better.html} } @INPROCEEDINGS{GrahamCumming03, author = {John Graham-Cumming}, year = 2003, title = {The Spammers' Compendium}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://popfile.sourceforge.net/SpamConference011703.pdf}}, keywords = {BAYESIAN}, url = {http://popfile.sourceforge.net/SpamConference011703.pdf} } @INPROCEEDINGS{GrahamCumming04, author = {John Graham-Cumming}, year = 2004, title = {How to Beat a Bayesian Spam Filter}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://www.jgc.org/SpamConference011604.pps}}, keywords = {BAYESIAN}, url = {http://www.jgc.org/SpamConference011604.pps} } @INPROCEEDINGS{Gray04, author = {Alan Gray and Mads Haahr}, year = 2004, title = {Personalised, Collaborative Spam Filtering}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/132.pdf}}, keywords = {COLLABORATIVE}, url = {http://www.ceas.cc/papers-2004/132.pdf} } @INPROCEEDINGS{Hall96, author = {{R.J.} Hall}, year = 1996, title = {Channels: Avoiding Unwanted Electronic Mail}, booktitle = {Proceedings of the {DIMACS} Symposium on Network Threats}, note = {Available: \url{ftp://ftp.research.att.com/dist/hall/papers/agents/channels-long.ps}}, keywords = {ADDRESS}, url = {ftp://ftp.research.att.com/dist/hall/papers/agents/channels-long.ps} } @ARTICLE{Hall98, author = {{R.J.} Hall}, month = {March}, year = 1998, title = {How to Avoid Unwanted Email}, journal = {Communications of the ACM}, note = {Available: \url{ftp://ftp.research.att.com/dist/hall/papers/agents/channels-long.ps}}, keywords = {ADDRESS}, url = {ftp://ftp.research.att.com/dist/hall/papers/agents/channels-long.ps} } @INPROCEEDINGS{Hershkof04, author = {Shlomo Hershkof}, year = 2004, title = {Behavior Based Spam Detection}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://www1.cs.columbia.edu/~sh553/MITSPAM04/}}, keywords = {TECHNICAL}, url = {http://www1.cs.columbia.edu/~sh553/MITSPAM04/} } @INPROCEEDINGS{Hird02, author = {S. Hird}, year = 2002, title = {Technical Solutions for Controlling Spam}, booktitle = {Proceedings of the Annual Meeting of the Australian {UNIX} and Open Systems User Group {(AUUG)}}, note = {Available: \url{http://security.dstc.edu.au/papers/technical_spam.pdf}}, keywords = {GENERAL}, url = {http://security.dstc.edu.au/papers/technical_spam.pdf} } @INPROCEEDINGS{Hulten04a, author = {Geoff Hulten and Joshua Goodman}, year = 2004, title = {Filtering Spam E-Mail on a Global Scale}, booktitle = {Proceedings of the World Wide Web Conference}, note = {Available: \url{http://research.microsoft.com/~joshuago/www2004-submission.pdf}}, keywords = {GENERAL}, url = {http://research.microsoft.com/~joshuago/www2004-submission.pdf} } @INPROCEEDINGS{Hulten04b, author = {Geoff Hulten and Anthony Penta and Gopalakrishnan Seshadrinathan and Manav Mishra}, year = 2004, title = {Trends in Spam Products and Methods}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/165.pdf}}, keywords = {BAYESIAN}, url = {http://www.ceas.cc/papers-2004/165.pdf} } @INPROCEEDINGS{Ioannidis03, author = {J. Ioannidis}, month = {February}, year = 2003, title = {Fighting Spam by Encapsulating Policy in Email Addresses}, booktitle = {Proceedings of the Symposium of Network and Distributed Systems Security {(NDSS)}}, note = {Available: \url{http://www.isoc.org/isoc/conferences/ndss/03/proceedings/papers/1.pdf}}, address = {San Diego, California}, keywords = {ADDRESS}, url = { http://www.isoc.org/isoc/conferences/ndss/03/proceedings/papers/1.pdf} } @UNPUBLISHED{Kelleher04, author = {Daniel Kelleher}, year = 2004, title = {Spam Filtering Using Contextual Network Graphs}, note = {Final Year Project in Computational Linguistics, Department of Computer Science, University of Dublin, (Trinity College), supervised by Dr. Padraig Cunningham, course 2003--04. Available: \url{http://www.cs.tcd.ie/courses/csll/dkellehe0304.pdf}}, keywords = {BAYESIAN}, url = {http://www.cs.tcd.ie/courses/csll/dkellehe0304.pdf} } @INPROCEEDINGS{Kolcz01, author = {Aleksander Kolcz and Joshua Alspector}, year = 2001, title = {{SVM}-based Filtering of E-mail Spam with Content-specific Misclassification Costs}, booktitle = {Proceedings of the TextDM'01 Workshop on Text Mining - held at the 2001 IEEE International Conference on Data Mining}, note = {Available: \url{http://www-ai.ijs.si/DunjaMladenic/TextDM01/papers/Kolcz_TM.pdf}}, keywords = {BAYESIAN}, abstract = {We address the problem of separating legitimate emails from uncolicited ones in the context of a large-scale operation, where the diversity of user accounts is very high, while misclassification costs are content-dependent and highly asymmetric. A category specific cost model is proposed and several effective methods of training a cost sensitive filter are studied, using a Support Vector Machine (SVM) as the base classifier. Clear benefits of explictly accounting for varied misclassification costs, either during training or as a form of post-processing, are shown.}, url = {http://www-ai.ijs.si/DunjaMladenic/TextDM01/papers/Kolcz_TM.pdf} } @INPROCEEDINGS{Kolcz04, author = {Aleksander Kolcz and Abdur Chowdhury and Joshua Alspector}, year = 2004, title = {The Impact of Feature Selection on Signature-Driven Spam Detection}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/147.pdf}}, keywords = {DUPLICATES}, url = {http://www.ceas.cc/papers-2004/147.pdf} } @INPROCEEDINGS{Kraut02, author = {Robert Kraut and Shyam Sunder and James Morris and Rahul Telang and Darrin Filer and Matt Cronin}, year = 2002, title = {Markets for Attention: Will Postage for Email Help?}, booktitle = {Proceedings of the 2002 {ACM} Conference on Computer Supported Cooperative Work, New Orleans, Louisiana, {USA}}, pages = {206--215}, note = {Available: \url{http://www.som.yale.edu/Faculty/sunder/Email/Emarket.pdf}}, publisher = {ACM Press}, address = {New York, NY}, keywords = {POSTAGE}, url = {http://www.som.yale.edu/Faculty/sunder/Email/Emarket.pdf} } @INPROCEEDINGS{Lamb04, author = {Marty Lamb}, year = 2004, title = {TarProxy: Lessons Learned and What's Ahead}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://www.martiansoftware.com/tarproxy/tarproxy_2004_spam_conference.pdf}}, keywords = {TECHNICAL}, url = { http://www.martiansoftware.com/tarproxy/tarproxy_2004_spam_conference.pdf} } @INPROCEEDINGS{Leiba04, author = {Barry Leiba and Nathaniel Borenstein}, year = 2004, title = {A Multifaceted Approach to Spam Reduction}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/127.pdf}}, keywords = {GENERAL}, url = {http://www.ceas.cc/papers-2004/127.pdf} } @INPROCEEDINGS{Lewis03, author = {David Lewis}, year = 2003, title = {(Spam vs.) Forty Years of Machine Learning for Text Classification}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://www.daviddlewis.com/publications/slides/lewis-2003-0117-spamconf-slides.pdf}}, keywords = {BAYESIAN}, url = { http://www.daviddlewis.com/publications/slides/lewis-2003-0117-spamconf-slides.pdf} } @INPROCEEDINGS{Li04, author = {Kang Li and Calton Pu and Mustaque Ahamad}, year = 2004, title = {Resisting SPAM Delivery by TCP Damping}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/191.pdf}}, keywords = {POSTAGE}, url = {http://www.ceas.cc/papers-2004/191.pdf} } @INPROCEEDINGS{Loder04a, author = {Thede Loder and Marshall {Van Alstyne} and Rick Wash}, year = 2004, title = {An Economic Solution to the Spam Problem}, booktitle = {Proceedings of the {ACM} Conference on Electronic Commerce}, note = {Available: \url{http://www.citi.umich.edu/u/rwash/pubs/spam-acm.pdf}}, keywords = {POSTAGE}, url = {http://www.citi.umich.edu/u/rwash/pubs/spam-acm.pdf} } @INPROCEEDINGS{Loder04b, author = {Thede Loder and Marshall Van Alstyne and Rick Wash}, year = 2004, title = {An Economic Solution to the Spam Problem}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://www.eecs.umich.edu/~tloder/abm_mit_spam_econ_14.ppt}}, keywords = {POSTAGE}, url = {http://www.eecs.umich.edu/~tloder/abm_mit_spam_econ_14.ppt} } @INPROCEEDINGS{Madigan04, author = {David Madigan}, year = 2004, title = {Statistics and the War on Spam}, booktitle = {Statistics, A Guide to the Unknown}, note = {Available: \url{http://www.stat.rutgers.edu/~madigan/PAPERS/sagtu.pdf}}, keywords = {BAYESIAN}, url = {http://www.stat.rutgers.edu/~madigan/PAPERS/sagtu.pdf} } @INPROCEEDINGS{Massey03, author = {Bart Massey and Mick Thomure and Raya Budrevich and Scott Long}, year = 2003, title = {Learning Spam: Simple Techniques for Freely-Available Software}, booktitle = {Proceeding of the 2003 Usenix Annual Technical Conference, Freenix Track}, note = {Available: \url{http://nexp.cs.pdx.edu/twiki-psam/pub/PSAM/PsamDocumentation/spam.pdf}}, keywords = {BAYESIAN}, url = { http://nexp.cs.pdx.edu/twiki-psam/pub/PSAM/PsamDocumentation/spam.pdf} } @INPROCEEDINGS{Meyer04, author = {T.A Meyer and B Whateley}, year = 2004, title = {SpamBayes: Effective open-source, Bayesian based, email classification system}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/136.pdf}}, keywords = {BAYESIAN}, url = {http://www.ceas.cc/papers-2004/136.pdf} } @INPROCEEDINGS{Michelakis04, author = {Eirinaios Michelakis and Ion Androutsopoulos and Georgios Paliouras and George Sakkis and Panagiotis Stamatopoulos}, year = 2004, title = {Filtron: A Learning-Based Anti-Spam Filter}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/142.pdf}}, keywords = {BAYESIAN}, url = {http://www.ceas.cc/papers-2004/142.pdf} } @INPROCEEDINGS{Nottelmann01, author = {Henrik Nottelmann and Norbert Fuhr}, year = 2001, title = {Learning probabilistic Datalog rules for information classification and transformation}, booktitle = {In Proceedings of the Tenth International Conference on Information and Knowledge Management (CIKM)}, note = {Available: \url{http://ls6-www.informatik.uni-dortmund.de/ir/publications/2001/Nottelmann_Fuhr:01.html}}, keywords = {BAYESIAN}, url = { http://ls6-www.informatik.uni-dortmund.de/ir/publications/2001/Nottelmann_Fuhr:01.html} } @INPROCEEDINGS{Obrien03, author = {Cormac O’Brien and Carl Vogel}, month = {September}, year = 2003, title = {Spam Filters: Bayes Vs. Chi-Squared; Letters Vs. Words}, booktitle = {Proceedings of the International Symposium on Information and Communication Technologies}, note = {Available: \url{http://www.cs.tcd.ie/publications/tech-reports/reports.03/TCD-CS-2003-13.pdf}}, keywords = {BAYESIAN}, url = { http://www.cs.tcd.ie/publications/tech-reports/reports.03/TCD-CS-2003-13.pdf} } @INPROCEEDINGS{Obrien04, author = {Cormac O'Brien and Carl Vogel}, month = {January}, year = 2004, title = {Comparing {SpamAssassin} with {CBDF} Email Filtering}, booktitle = {Proceedings of the 7th Annual {CLUK} Research Colloquium}, note = {Available: \url{http://www.cs.tcd.ie/Cormac.OBrien/spamAss.pdf}}, keywords = {BAYESIAN}, url = {http://www.cs.tcd.ie/Cormac.OBrien/spamAss.pdf} } @INPROCEEDINGS{Oda03a, author = {T. Oda and T. White}, year = 2003, title = {Increasing the Accuracy of a Spam-Detecting Artificial Immune System}, booktitle = {Proceedings of the Congress on Evolutionary Computation {(CEC} 2003), Canberra, Australia}, pages = {390--396}, note = {Available: \url{http://terri.zone12.com/doc/academic/spam_cec2003.pdf}}, keywords = {BAYESIAN}, url = {http://terri.zone12.com/doc/academic/spam_cec2003.pdf} } @INPROCEEDINGS{Oda03b, author = {T. Oda and T. White}, year = 2003, title = {Developing an Immunity to Spam}, booktitle = {Genetic and Evolutionary Computation - GECCO 2003. Genetic and Evolutionary Computation Conference, Chicago, IL, USA. Lecture Notes in Computer Science, Vol. 2723, Springer}, pages = {231--242}, note = {Available: \url{http://terri.zone12.com/doc/academic/spam_gecco2003.pdf}}, keywords = {BAYESIAN}, url = {http://terri.zone12.com/doc/academic/spam_gecco2003.pdf} } @INPROCEEDINGS{Pantel98, author = {Patrick Pantel and Dekang Lin}, year = 1998, title = {{SpamCop}: A Spam Classification and Organization Program}, booktitle = {Learning for Text Categorization: Papers from the 1998 Workshop}, note = {Available: \url{http://www.cs.ualberta.ca/~ppantel/Download/Papers/aaai98.pdf}}, publisher = {AAAI Technical Report WS-98-05}, address = {Madison, Wisconsin}, keywords = {BAYESIAN}, url = {http://www.cs.ualberta.ca/~ppantel/Download/Papers/aaai98.pdf} } @INPROCEEDINGS{Praed03, author = {Jon Praed}, year = 2003, title = {A Spam Litigator's View from the Front Lines}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://spamconference.org/praed.pdf}}, keywords = {OTHER}, url = {http://spamconference.org/praed.pdf} } @TECHREPORT{Provost99, author = {Jefferson Provost}, year = 1999, title = {Naive-Bayes vs. Rule-Learning in Classification of Email}, note = {Available: \url{http://www.cs.utexas.edu/users/jp/research/email.paper.pdf}}, institution = {Dept. of Computer Sciences at the U. of Texas at Austin}, keywords = {BAYESIAN}, url = {http://www.cs.utexas.edu/users/jp/research/email.paper.pdf} } @INPROCEEDINGS{Rennie03, author = {Jason Rennie}, year = 2003, title = {Automatic Feature Induction for Text Classification}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://people.csail.mit.edu/~jrennie/talks/spam03.pdf}}, keywords = {BAYESIAN}, url = {http://people.csail.mit.edu/~jrennie/talks/spam03.pdf} } @INPROCEEDINGS{Rigoutsos04, author = {Isidore Rigoutsos and Tien Huynh}, year = 2004, title = {Chung-Kwei: a Pattern-discovery-based System for the Automatic Identification of Unsolicited E-mail Messages (SPAM)}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/153.pdf}}, keywords = {BAYESIAN}, url = {http://www.ceas.cc/papers-2004/153.pdf} } @INPROCEEDINGS{Rios04, author = {Gordon Rios and Hongyuan Zha}, year = 2004, title = {Exploring Support Vector Machines and Random Forests for Spam Detection}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/174.pdf}}, keywords = {BAYESIAN}, url = {http://www.ceas.cc/papers-2004/174.pdf} } @INPROCEEDINGS{Sahami98, author = {Mehran Sahami and Susan Dumais and David Heckerman and Eric Horvitz}, year = 1998, title = {A Bayesian Approach to Filtering Junk E-Mail}, booktitle = {Learning for Text Categorization: Papers from the 1998 Workshop}, note = {Available: \url{http://robotics.stanford.edu/users/sahami/papers-dir/spam.ps}}, publisher = {AAAI Technical Report WS-98-05}, address = {Madison, Wisconsin}, keywords = {BAYESIAN}, url = {http://robotics.stanford.edu/users/sahami/papers-dir/spam.ps} } @INPROCEEDINGS{Sakkis01, author = {Georgios Sakkis and Ion Androutsopoulos and Georgios Paliouras and Vangelis Karkaletsis and Constantine D. Spyropoulos and Panagiotis Stamatopoulos}, year = 2001, title = {Stacking Classifiers for Anti-Spam Filtering of E-Mail}, booktitle = {Proceedings of EMNLP-01, 6th Conference on Empirical Methods in Natural Language Processing}, note = {Available: \url{http://www.arxiv.org/abs/cs.CL/0106040}}, publisher = {Association for Computational Linguistics, Morristown, US}, address = {Pittsburgh, US}, keywords = {BAYESIAN}, url = {http://www.arxiv.org/abs/cs.CL/0106040} } @ARTICLE{Sakkis03, author = {G. Sakkis and I. Androutsopoulos and G. Paliouras and V. Karkaletsis and {C. D.} Spyropoulos and P. Stamatopoulos}, year = 2003, title = {A Memory-Based Approach to Anti-Spam Filtering for Mailing Lists}, journal = {Information Retrieval Journal}, volume = 6, number = 1, note = {Available: \url{http://www.eden.rutgers.edu/~gsakkis/docs/IR2003.pdf}}, keywords = {BAYESIAN}, url = {http://www.eden.rutgers.edu/~gsakkis/docs/IR2003.pdf} } @INPROCEEDINGS{Salib03, author = {Michael Salib}, year = 2003, title = {Heuristics in the Blender}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://web.mit.edu/msalib/www/writings/talks/spam-filtering-conference/spam-presentation.pdf}}, keywords = {BAYESIAN}, url = { http://web.mit.edu/msalib/www/writings/talks/spam-filtering-conference/spam-presentation.pdf} } @INPROCEEDINGS{Schneider03, author = {{Karl-Michael} Schneider}, year = 2003, title = {A Comparison of Event Models for Naive Bayes Anti-Spam E-Mail Filtering}, booktitle = {Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics {(EACL'03)}}, note = {Available: \url{http://www.phil.uni-passau.de/linguistik/mitarbeiter/schneider/pub/eacl2003.pdf}}, keywords = {BAYESIAN}, url = { http://www.phil.uni-passau.de/linguistik/mitarbeiter/schneider/pub/eacl2003.pdf} } @INPROCEEDINGS{Schneider04, author = {Karl-Michael Schneider}, year = 2004, title = {Learning to Filter Junk E-Mail from Positive and Unlabeled Examples}, booktitle = {Proceedings of the 1st International Joint Conference on Natural Language Processing {(IJCNLP}-04), Sanya City, Hainan Island, China}, pages = {602--607}, note = {Available: \url{http://www.phil.uni-passau.de/linguistik/mitarbeiter/schneider/pub/ijcnlp2004.pdf}}, keywords = {BAYESIAN}, url = { http://www.phil.uni-passau.de/linguistik/mitarbeiter/schneider/pub/ijcnlp2004.pdf} } @INPROCEEDINGS{Segal04, author = {Richard Segal and Jason Crawford and Jeffrey Kephart and Barry Leiba}, year = 2004, title = {SpamGuru: An Enterprise Anti-Spam Filtering System}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/126.pdf}}, keywords = {GENERAL}, url = {http://www.ceas.cc/papers-2004/126.pdf} } @ARTICLE{Seigneur04, author = {{Jean-Marc} Seigneur and {Christian Damsgaard} Jensen}, year = 2004, title = {Privacy Recovery with Disposable Email Addresses}, journal = {IEEE Security and Privacy}, volume = 1, number = 6, pages = {35--39}, note = {Available: \url{http://www.computer.org/security/v1n6/j6sei.htm}}, keywords = {ADDRESS}, url = {http://www.computer.org/security/v1n6/j6sei.htm} } @INPROCEEDINGS{Sergeant03, author = {Matt Sergeant}, year = 2003, title = {Internet Level Spam Detection and SpamAssassin 2.50}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://axkit.org/docs/presentations/spam/SpamConf2003.ppt}}, keywords = {BAYESIAN}, url = {http://axkit.org/docs/presentations/spam/SpamConf2003.ppt} } @INPROCEEDINGS{Siefkes04, author = {Christian Siefkes and Fidelis Assis and Shalendra Chhabra and William S. Yerazunis}, editor = {Jean-Fran{\c c}ois Boulicaut and Floriana Esposito and Fosca Giannotti and Dino Pedreschi}, year = 2004, title = {Combining {Winnow} and Orthogonal Sparse Bigrams for Incremental Spam Filtering}, booktitle = {Proceedings of the 8th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2004)}, series = {Lecture Notes in Artificial Intelligence}, volume = 3202, pages = {410--421}, note = {Available: \url{http://www.siefkes.net/papers/winnow-spam.pdf}}, publisher = {Springer}, keywords = {BAYESIAN}, url = {http://www.siefkes.net/papers/winnow-spam.pdf} } @MASTERSTHESIS{Stone03, author = {Trevor Stone}, year = 2003, title = {Parameterization of Nave Bayes for Spam Filters}, note = {Available: \url{http://trevorstone.org/school/spamfiltering.pdf}}, school = {University of Colorado at Boulder}, type = {Masters Comphrehensive Exam}, keywords = {BAYESIAN}, url = {http://trevorstone.org/school/spamfiltering.pdf} } @INPROCEEDINGS{Sullivan04, author = {Terry Sullivan}, year = 2004, title = {The more things change: Volatility and stability in spam features}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://www.qaqd.com/research/mit04sum.html}}, keywords = {BAYESIAN}, url = {http://www.qaqd.com/research/mit04sum.html} } @INPROCEEDINGS{Twining04, author = {{Richard Daniel} Twining and {Matthew M.} Williamson and Miranda Mowbray and Maher Rahmouni}, year = 2004, title = {E-mail Prioritization: reducing delays on legitimate mail caused by junk mail}, booktitle = {Proceedings of {USENIX} 2004 Annual Technical Conference, General Track}, pages = {45--58}, note = {Available as HP Tech Report HPL-2004-5R.1, \url{http://www.hpl.hp.com/techreports/2004/HPL-2004-5.pdf}}, keywords = {TECHNICAL}, url = {http://www.hpl.hp.com/techreports/2004/HPL-2004-5.pdf} } @ARTICLE{Tompkins03, author = {T. Tompkins and D. Handley}, month = {September}, year = 2003, title = {Giving e-Mail Back to the Users: Using Digital Signatures to Solve the Spam Problem}, journal = {First Monday}, volume = 8, number = 9, note = {Available: \url{http://firstmonday.org/issues/issue8_9/tompkins/index.html}}, keywords = {SIGNATURE}, url = {http://firstmonday.org/issues/issue8_9/tompkins/index.html} } @INPROCEEDINGS{Watson04, author = {Brett Watson}, year = 2004, title = {Beyond Identity: Addressing Problems that Persist in an Electronic Mail System with Reliable Sender Identification}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/140.pdf}}, keywords = {TECHNICAL}, url = {http://www.ceas.cc/papers-2004/140.pdf} } @ARTICLE{Weinstein03, author = {Lauren Weinstein}, month = {Aug}, year = 2003, title = {Inside Risks: {S}pam Wars}, journal = {CACM}, volume = 46, number = 8, pages = 136, note = {Available: \url{http://www.csl.sri.com/users/neumann/insiderisks.html#158}}, keywords = {GENERAL}, url = {http://www.csl.sri.com/users/neumann/insiderisks.html#158} } @INPROCEEDINGS{Wittel04, author = {Gregory L. Wittel and S. Felix Wu}, year = 2004, title = {On Attacking Statistical Spam Filters}, booktitle = {Proceedings of the First Conference on Email and Anti-Spam (CEAS)}, note = {Available: \url{http://www.ceas.cc/papers-2004/170.pdf}}, keywords = {BAYESIAN}, url = {http://www.ceas.cc/papers-2004/170.pdf} } @INPROCEEDINGS{Yerazunis03, author = {Bill Yerazunis}, year = 2003, title = {Sparse Binary Polynomial Hash Message Filtering and The CRM114 Discriminator}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://crm114.sourceforge.net/CRM114_paper.html}}, keywords = {BAYESIAN}, url = {http://crm114.sourceforge.net/CRM114_paper.html} } @INPROCEEDINGS{Yerazunis04, author = {Bill Yerazunis}, year = 2004, title = {The Plateau at 99.9% Accuracy, and How to Get Past It}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://crm114.sourceforge.net/Plateau_Paper.pdf}}, keywords = {BAYESIAN}, url = {http://crm114.sourceforge.net/Plateau_Paper.pdf} } @INPROCEEDINGS{Zdziarski04, author = {Jonathan Zdziarski}, year = 2004, title = {Advanced Language Classification using Chained Tokens}, booktitle = {Proceedings of the Spam Conference}, note = {Available: \url{http://www.nuclearelephant.com/papers/chained.html}}, keywords = {BAYESIAN}, url = {http://www.nuclearelephant.com/papers/chained.html} }