IBM Security announced on Tuesday its artificial intelligence (AI) program Watson would be trained to tackle cybercrime. The AI will reportedly be trained to provide insights and solution to cybersecurity threats presented via Watson for Cyber Security, a cloud service.
The project is apparently a collaboration between IBM Security and eight universities, and is expected to last up to a year. IBM Security over the past year has been preparing Watson for this endeavour, feeding it cybersecurity-related information so the AI can identify what a threat is, PC World reported.
According to Kevin Skapinetz, director of strategy for IBM Security, a lot of information about threats is located in blogs, reports and research documentation, which are largely unstructured, and IBM Security is training Watson to go through the information and understanding what it all means.
"Let's say tomorrow there's an article about a new type of malware, then a bunch of follow-up blogs," Skapinetz explained. "Essentially what we're doing is training Watson not just to understand that those documents exist but to add context and make connections between them."
The collaboration with the universities will result in Watson being fed up to 15,000 documents a month, ranging from threat reports, strategies, databases and materials from IBM's X-Force research library, which includes over 20 years of research.
Noting that over 60,000 security blogs are published each year, Skapinetz believes analysts are missing out on a lot of information. "What we're aiming to do is take away some of the guesswork and help analysts understand more context with an always-on advisor that can help investigate and answer questions," he said.
IBM Security hopes to bring out a beta version of Watson for Cyber Security later this year.