VANCOUVER, British Columbia – March 31, 2003 – ActiveState Corp., the leader in email content filtering software, today announced the creation of an internal blue ribbon team comprised of the world's foremost anti-spam researchers. The Task Force members include: Dr. John Graham-Cumming, creator of the popular open source Perl-based Bayesian mail filtering program, POPfile; Tim Peters, creator of SpamBayes, a Python-based open source Bayesian email classifier; Jason Rennie of MIT's Artificial Intelligence lab and creator of the open source tool iFile, an automated email classification system; and Gary Robinson, an innovator in collaborative filtering. The Task Force is focusing on anti-spam issues affecting the enterprise, and is led by ActiveState's Director of Development, Jesse Dougherty.
Industry analysts Ferris Research estimates that spam will cost corporate America over $10 billion in lost productivity in 2003 alone. The annual cost is expected to double as the amount of spam to U.S. businesses increases from approximately 25% of all email today, to nearly 50% in 2008. Spammers are becoming increasingly more sophisticated in their techniques, adopting new methods to foil spam-blocking software. The adaptive filtering approach of the Task Force has the predictive capability to identify these methods and their first technical developments will be seen by ActiveState's PureMessage customers as early as April in the regular spam engine updates.
"Clearly, the tactics of spammers necessitate a technical solution that can evolve to meet their increasing complexity," said Marten Nelson, Senior Analyst, Ferris Research. "The Bayesian approach is one of the interesting new technologies being developed to accurately identify spam. A technology that learns as it analyzes email is the type of sophisticated system that is required in order to adapt 'on-the-fly'."
The Anti-spam Task Force is focusing on several technical initiatives to optimize enterprise email messaging, including:
- Developing "next generation" methods for analyzing email content to more accurately distinguish between desirable and undesirable email
- Pioneering the development of non-spam gateway email filtering features to enhance organizational productivity
- Identifying and facilitating collaboration within the messaging industry to implement standards and email policies
"Spam mutates amazingly fast by using increasingly complex encoding to try to avoid identification. And that is spam's Achilles heel: spammers' increasingly complicated bag of tricks will end up giving them away, and help create the solution for us," said Dr. John Graham-Cumming. "I have no doubt that as a team we'll find many ways to spot and stop spam in its tracks."
"Individually, the team members have produced cutting-edge work in anti-spam technologies that is widely accepted as industry standard. Collectively, their achievements will be revolutionary in their ability to accurately identify spam," said Jesse Dougherty, Director of Development, ActiveState. "One of the primary problems to date has been the issue of false positives. An anti-spam system that can learn from experience and adapt is the new approach that's needed to reach near 100% accuracy."
