Watson takes on cybersecurity
- By Derek Major
- May 17, 2016
IBM Security has announced Watson for Cyber Security, a cloud-based version of its natural language processing platform that will automate the connections in unstructured data to improve security analysts’ capabilities. IBM’s X-Force library, which includes 20 years of security research on 8 million spam and phishing attacks and more than 100,000 documented vulnerabilities, will provide most of the materials that will be fed to Watson starting later this year.
Watson’s ability to learn from unstructured data that traditional security tools cannot process -- including blogs, articles, videos, reports, alerts and other information -- will allow it to provide insight and recommendations on emerging threats, the company said. Watson’s data mining and graphical presentation tools, as well as its ability to find connections among related data points in different documents, will also be tapped for the new application.
To train the system for cybersecurity, IBM will work with eight universities to initially help build Watson's knowledge base by annotating and feeding it up to 15,000 security documents per month, which will help it understand hashes, infection methods and indicators of compromise and help identify advanced persistent threats. Students will gain hands-on experience in the emerging field of cognitive security.
The universities involved in the project include California State Polytechnic University at Pomona, Pennsylvania State University, Massachusetts Institute of Technology, New York University, University of Maryland Baltimore County, the University of New Brunswick, the University of Ottawa and the University of Waterloo.
Derek Major is a former reporter for GCN.