Among the more innovative techniques currently available to defeat spam is one offered by Abaca. Instead of relying on the reputation of the sender or scanning the content of incoming e-mail as many antispam solutions do, the Abaca system determines the reputation of e-mail recipients based on the proportion of spam that they receive. (Compare antispam products)

The concept behind Abaca’s receiver reputation model is that different individuals receive differing amounts of spam and legitimate e-mail. When analyzing a message, each receiver’s percentage of spam received vs. legitimate e-mail received establishes a reputation rating for each recipient. In short, if a message is sent to users who typically receive a high percentage of spam, the Abaca model assumes that the message is more likely to be spam. However, if the message is sent to users who typically receive a low percentage of spam, the message is more likely to be legitimate. Aggregating the reputations of all recipients of a particular message, therefore, is equivalent to combining those users’ ratings to estimate the legitimacy of the sender and the message. 

In Abaca’s system, the key determinant of whether a message is spam or legitimate is not based on the identity of the sender or the content of the e-mail, but instead the reputations of the e-mail recipients, individually and collectively.

Abaca’s technology is ReceiverNet, a patent-pending approach. The technique is new and quite different from other antispam solutions currently on the market. ReceiverNet is based on a sophisticated mathematical formula that uses receiver reputations to accurately differentiate spam from legitimate messages. Abaca claims that its spam capture efficiency is 99.7% and will generate an extremely low level of false positives – fewer than 130 false positives for every 1 million messages received.

Abaca’s Email Protection Gateway appliance with a low price point and 99% filtering accuracy guarantee, is definitely worth a look.

Michael Osterman is principal analyst of Osterman Research.