The classifier is focused on Web server malware or, put more simply, the hacking and hijacking of a website that is then used to attack all its visitors.
If it is possible to accurately predict which sites and servers are most at-risk, it becomes easier to keep an eye on and warn against dangerous websites, the researchers say. Website operators can be alerted ahead of an attack, and search engines can easily know which websites to keep an eye on for potential exclusion from search results.
The algorithm is designed to automatically detect whether a Web server is likely to become malicious in the future by analyzing a wide array of the site’s characteristics: For example, what software does the server run? What keywords are present? How are the Web pages structured? If your website has a whole lot in common with another website that ended up hacked, the classifier will predict a gloomy future.
The classifier itself always updates and evolves, the researchers wrote. It can “quickly adapt to emerging threats.”
An anonymous reader writes: A new research paper outlines new software that scans and scrapes web sites from today and the past, learns patters about what happens prior to a security breach, and then accurately predicts what websites will be hacked in the future. The new tool is up to 66% accuracy.