At OpenDNS Labs we have developed a number of predictive models to hunt down evil on the Internet. We have discussed in previous blogs and conferences our algorithms NLPRank , Spike detector , and malicious IP space/rogue host detectors (section 14).
In this blog we will discuss how we integrate all of these detection models to improve detection coverage of current threats and walk through a few interesting examples.
Phishing and Spikes
One of the recent samples we have found was a Facebook phishing campaign that was surfaced by our real-time alert system. Our ...