STRATO announces new, most-effective filter to combat picture spam
Pictures boost spam to over 90% of all E-mail traffic
Spam is on the increase in the form of picture spam and STRATO, one of Europe’s leading web hosts, has developed an extremely effective picture spam filter to help combat the problem.
“As the name suggests, picture spam uses graphics instead of text and the problem with most conventional filters is that they do not detect pictures,” said René Wienholtz, CTO at STRATO. “GIF attachments, or text contained in pictures can not be examined by traditional E-mail filters”.
Since 2005, STRATO has been developing its new picture spam filter with the Institute of Computer Technology at the Humboldt University Berlin. “STRATO handles over two billion E-mails per month which illustrates the extent of current E-mail traffic,” added Wienholtz. “Spam senders are exploiting the fact that picture spam is a relatively new phenomenon and there are few solutions on the market able to tackle the problem effectively.”
As a result of the emergence of picture spam, spam as a whole has risen from between 75% and 80% of all E-mail traffic to over 90% in the last three months. STRATO’s picture spam filter uses a new technique called ‘Fingerprinting’ developed in collaboration with Professor Scheffer, a computer science expert now working for the renowned Max-Planck-Institute,.
The pictures contained within a spam-wave leave an individual fingerprint. Recognised by the new technique and a clear sign of picture spam, is if mass-mailed pictures, sent in one stroke, have similar characteristics or fingerprints. Corresponding fingerprints can be generated by colour distribution, for example a certain colour percentage in a specific tone, or by the composition or structure of the individual graphics. If similar, these characteristics will reveal a common sender or identical content.
Scheffer said: “Fingerprinting currently provides the best possible protection against picture spam. No single spam picture is identical to another and the perpetrators of spam automatically create millions of variations of their spam E-mail, which differ in some details but appear identical on screen. Fingerprinting allows picture spam to be identified via similar characteristics. Without Fingerprinting, each individual picture would need to be analysed which is an impossible task”.
Used in conjunction with STRATO’s ServerSide Security spam filter, also developed in conjunction with the Humboldt University, Fingerprinting ensures the highest spam detection rate currently available.
Wienholtz added: “STRATO reliably delivers desired E-mails and our spam filters make the junk folder obsolete, meaning time is not wasted sifting through the junk folder in the search for wanted emails. Spam senders are constantly working to outsmart filters, but at STRATO we constantly develop our systems to join them. We are currently working to develop a filter which will learn from the spam senders’ tactics and develop the corresponding countermeasures to stay a step ahead of them. This is made possible by self-improving algorithms, a method whereby a new type of picture spam is recognised and then added to the filter’s repertoire, so no mistake is repeated. Programmers try to anticipate the spam senders next moves and write the algorithms accordingly using Games theory, a type of mathematical chess game. Our aim is to detect tomorrow’s spam, today”.
