Security data scientists on how to make your data useful
Data science and machine learning can reveal valuable security information that would otherwise remain hidden in large data sets. Security data scientists can be hard to find and may be out of reach for most organizations. Even without these skill sets, companies can make strides to take advantage of advanced analytics to improve their security posture.
In August 2017, Google data scientists revealed that they had worked in conjunction with academic researchers from Princeton and other universities to create a model for tracking ransomware payments on the bitcoin blockchain. The researchers tallied roughly 20,000 payments worth $16 million.
"Very large organizations can often build their own data storage and data analysis solutions, because they will often have security data scientists on staff to write code and identify patterns," said Joshua Saxe, chief data scientist at security software firm Sophos. "The vast majority of organizations do not have the resources to do that."
Data analytics and machine learning can help companies quickly reduce the amount of data they need to parse in order to highlight potential threats. Too much data noise can quickly overwhelm human analysts, however. In this issue of Information Security magazine, we talk to CISOs and security data scientists about effective use of data analytics, machine learning and their strategies for managing this information to advance threat research.