Spam filtering is tremendously difficult to get right; to reach today’s levels of filter accuracy, anti-spam technologists over the years have invested huge amounts of financial and intellectual capital.
Filtering spam email isn’t just about sifting through email content, to find suspicious words or phrases. While that was certainly true ten years ago, today’s filters are completely different.
Spam filters sift through your incoming email and automatically decide which are spam and which are legitimate – or ham
It’s tremendously difficult to get right, but today’s state-of-the-art spam filters achieve levels of accuracy that would have been unthinkable a few years ago.
Spam filters have a huge arsenal of techniques available to them. In the jargon of computer performance, some techniques are more expensive than others – that is, they need more computer horsepower
Typically, a filter starts with the least expensive tests and performs more and more expensive tests until it’s sure whether the message is spam or ham.
It does that by combining the results of all the tests made so far (the result is sometimes known as a cocktail spam score). Tests that analyse the message content tend to be the most expensive, so they’re actually rarely used.
So, despite what many people believe, looking for certain tell-tale words and phrases is no longer the most common test for spam.
The most sophisticated content-scanning techniques were hailed as revolutionary a few years ago, but now they’re reserved for the most difficult-to-identify email.