Everyone knows there's no shortage of malicious activity on the internet.If you believe the hype, cyberspace is actually dominated by it. The question everyone needs answered, is how to avoid it. Today, computer scientists outline a new way of predicting the next attack so that you can block it well in advance.
This new technique builds on the most common technique for avoiding unwanted internet activity: creating lists of the most prolific attack sources and then compiling, sharing and finally blocking them. But the problem with these 'blacklists' is that the process is reactive: it blocks malicious sites only after they have attacked.
Last year, computer scientists began exploring a potentially more effective approach: predicting the sites most likely to attack and blocking them before they get the chance. The technique, called highly predictive blacklisting, uses data from any past attacks to create a graph out of the pattern of links between victims. When this is done, it runs an algorithm for each victim, looking for the most relevant attackers. The reuslting list is then used to block potential attackers in the future.
While this sounds like a brilliant idea, there are of course some problems to remedy. For example. the team isn't quite sure how to handle the constantly changing pattern of malicious attacks, while attackers may soon find that it's not actually difficult to fool recommendation systems if you try hard enough.
Nevertheless, this an impressive study that could be rapidly implemented. And if that happens, recommendation systems may soon be providing you not only with books and movie tips, but a happier and safer surfing experience as well. Courtesy of technologyreview.com