2004 · 173 citations · 6 references
ComputingComputer ScienceCybersecurityComputer SecurityStatistical LearningStatisticsAdversary TechniquesAnti-analysis TechniquesIntrusion DetectionStatistical AnalysisSpam DetectionSpam Filtering
The efforts of anti-spammers and spammers has often been described as an arms race. As we devise new ways to stem the flood of bulk mail, spammers respond by working their way around the new mechanisms. Their attempts to bypass spam filters illustrates this struggle. Spammers have tried many things from using HTML layout tricks, letter substitution, to adding random data. While at times their attacks are clever, they have yet to work strongly against the statistical nature that drives many filtering systems. The challenges in successfully developing such an attack are great as the variety of filtering systems makes it less likely that a single attack can work against all of them. Here, we examine the general attack methods spammers use, along with challenges faced by developers and spammers. We also demonstrate an attack that, while easy to implement, attempts to more strongly work against the statistical nature behind filters.
6
A Bayesian Approach to Filtering Junk E-Mail
Mehran Sahami, Susan Dumais, David Heckerman et al. · 1998 · 1.2K citations
An evaluation of Naive Bayesian anti-spam filtering
Ion Androutsopoulos, John Koutsias, Konstantinos V. Chandrinos et al. · arXiv (Cornell University) · 2000 · 529 citations · Full text
Boosting Trees for Anti-Spam Email Filtering
Xavier Carreras, Lluı́s Màrquez · ArXiv.org · 2001 · 344 citations · Full text
Support vector machines for text categorization
Avik Basu, Clarence P. Walters, Michael Shepherd · 2003 · 146 citations