London, UK: OpenDNS has unveiled NLPRank, a new model for advanced threat detection that applies algorithms most commonly used in fields like bioinformatics and data mining—not information security. Designed by OpenDNS security researcher Jeremiah O’Connor, NLPRank is based on natural language processing techniques that, combined with OpenDNS’s global network data, build an advanced threat detection lexicon—essentially a ‘malicious language of the Internet’ that can detect threatening domains in realtime. NLPRank specifically predicts both opportunistic phishing campaigns and attacks directed at highvalue targets such as financial institutions.
“Companies that have to deal with spear phishing attacks on a regular basis are very excited about this model,” said O’Connor. “It’s one of the only ways to detect spear phishing campaigns without analyzing malware in detail.”