SafeDNS uses machine learning to detect malicious internet resources

website magnifying glass www

However careful you are online it's always possible to get caught out by a maliciously coded website or advert that leads to malware ending up on your machine.

Online safety service SafeDNS is launching a new system for detecting malicious internet resources, which it claims blocks close to 100 percent of them for better online protection.

Using continuous machine learning and user behavior analysis, the new SafeDNS system takes a step forward from static lists of categorized resources to dynamically created databases. The SafeDNS research team has produced a technology able to detect malicious internet resources with 98 percent precision.

"This unparalleled technology developed by the company's research team takes SafeDNS to a different, much higher level -- on par with global leaders of the industry, as our ability to detect and filter out malware and botnets has significantly improved," says Dmitry Vostretsov, CEO of SafeDNS. "The technology gives SafeDNS a competitive edge as it detects malicious resources overlooked by the analogous systems of other vendors".

It works by processing and analyzing data from the company's filtering service to pinpoint malicious resources. One of the most important attributes used is group activity, malicious resources tend to be requested by a group of users over a short period of time such as a few hours. If a resource is legitimate it's requested by occasional users, rather than a fixed group of them, this pattern can be used to identify and blacklist malicious sites.

Sites are ranked on a continuous basis and the information fed into the SafeDNS database, which drives its filtering system. Information provided by the new system is also available for use through the company's open API of categorized internet resources.

More information on SafeDNS for home and business use is available on the company's website.

Photo Credit: Yuriy Boyko/Shutterstock

© 1998-2018 BetaNews, Inc. All Rights Reserved. Privacy Policy - Cookie Policy.