I know you're all probably sick of spam by now. I don't mean the unwanted messages clogging your inboxes, riddled with malicious links and with tempting offers of pills and powders and advice on stocks and shares. I mean the vendors who keep harping on about their solutions being the best at stopping this new epidemic of spam…well, to be honest, it doesn't seem anyone's is that good, because there's still an epidemic, isn't there? It's slowing down corporate networks as in-house systems are overwhelmed by the number and size of newer, image-based spam messages...or so they say.

Most traditional filters are unable to detect this new breed of spam and block it effectively because those clever spammers manage to make thousands of variations, each with one tiny fraction of the images altered, so that the new message sails clean through. So what to do? German web hosting firm Strato thinks it has the answer with its fingerprinting technology. Developed in partnership with the Institute of Computer Technology at the Humboldt University Berlin – boffins, white coats, you get the picture – and a certain Professor Scheffer of the Max-Planck-Institute – uber boffin - this technology works by not trying to identify every detail in a picture, but assessing the percentage of a certain colour in a specific tone, or by "the composition or structure of individual graphics", according to Strato. It then decides the probability of that spam mail coming from the same sender as another, and is therefore able to block it. Identifying similar but not identical characteristics in this way gets around those pesky spammers' ploy to bypass filters by changing minute details of the image.

Another key feature is called social graphs, which looks at the relationships between senders and receivers of mails and decides if a message being sent to your inbox is likely to have come from a particular sender. If this probability is low, chances are it is spam. There's more on the way from these clever Germans too, apparently, but I was not privy to that information when we met this week, because the patents have yet to be filed. It all sounds very exciting though…a self-learning spam filter with personalised filters for individuals.