Arovax NoSpam will attempt to classify incoming email messages as 'spam'. This means you can have spam automatically filed away in a SPAM mail folder, where it won't interrupt your email reading. First Arovax NoSpam must be trained by each user to identify spam and non-spam. In simple words, you should show Arovax NoSpam an email that you like and an email you don't like (spam). Arovax NoSpam will then analyze emails for clues as to what makes the spam and non-spam emails different. For example: different words, differences in the mailer headers and content style. The system then uses these clues to examine new messages.

For instance, the word "Nigeria" often appears in spam, so you could use a spam filter which identifies anything containing this word as spam. But what if your business involves writing a guidebook on Nigerian Wildlife Conservation? Clearly a more flexible approach is necessary. Additionally spammers will adapt their content over time and will no longer use the word "Nigeria" (or the words "Lose Weight Fast", or any of other common lines). Ideally, the software should be able to adapt as the spam changes.

Content-based trainable filters against Blacklist-Based

Arovax NoSpam is trainable. Some users avoid trainable spam filters, because they believe that training is a long and tiresome process, which leads to filtering based on obscure and fuzzy criteria. These users prefer filters based on blacklists such as SpamCop, ORDB, DSBL, SPEWS, etc.

They are wrong due to two facts:

1) A blacklist is NOT an objective criteria. Let's take a look at how a typical blacklist operates. Say, there's some web hosting company that sells email services. And say, there's some client who decides one day to send out a bunch of spams to a lot of addresses. Some of these might get submitted to a blacklist as spam. What happens is the web host's IP address or a group of IP addresses gets blacklisted. As a result, you stop receiving legitimate correspondence from this network, which is quite probably located in your own city.

Of course you can find excuses like: it was a bad web hosting company or it had bad clients. Well, that might be true, but it’s not the point. While the “bad software company” investigates that the problem was in a single “bad” client, a whole bunch of good and innocent clients would suffer. Is that objective enough? We don't think so.

2) Statistics-based criteria IS objective. Roughly, a statistics-based filter analyses each word that it finds in an email and compares it to the entry of the same word in its database, where there's a spam coefficient for it. The word-based approach has had a number of poor implementations, which might have spoiled the perception of this method. These filters came with a number of pre-defined words/coefficients and raised the spam probability of a message by simply incrementing a spam score of the message. The items that increased the spam score could be unsubscribe instructions, non-white HTML backgrounds or such words as "free" or "spam". These filters were known as "newsletter killers", because if there are two things that are present in most legitimate newsletters, this would be unsubscribe instructions and ads for free giveaways. Newsletter publishers went mad and started using tricks to fool these filters by typing "sp*m" or "fre*e". Well, that is subjective, but there's a great difference in how Arovax NoSpam works.

First, the formula that calculates the total spam score is not that simple (not linear). It does not work by simply adding up the coefficients or increasing a spam score, but deploys other criteria such as the overall message size. E.g. if there's a dozen of spam words in a long email about cooking, Arovax NoSpam will not mark it as spam.

Second, Arovax NoSpam is trainable. Not configurable, but trainable. That is you cannot tune the coefficients manually, but you can only submit a full message for training. This ensures objectivity by avoiding human errors and also means that your statistical coefficients are based on your personal email.

Both of the above ensure that Arovax NoSpam's approach is objective and is capable of providing great results.