Security analytics vendor Niara has raised $20 million in a Series B round of financing, bringing its total funding to date up to $29.4 million. The new funding round, led by Venrock and including the participation of New Enterprise Associates and Index Ventures, will help Niara develop its big data security analytics technology.
Niara aims to emerge from stealth mode and launch its security analytics platform for general availability in the second quarter of 2015.
The goal at Niara is to find the most sophisticated types of attacks, said Niara CEO and co-founder Sriram Ramachandran, who has worked in the engineering departments of technology vendors, including Sun Microsystems, Netscreen, Juniper Networks and Aruba Networks.
"Let's say, for example, an organization has a firewall at the perimeter of its network, and an attacker through malicious means is able to compromise a username and password; the attacker can just walk in through the front door," Ramachandran told eWEEK. "That's an example of the kind of sophisticated threat that many existing tools simply cannot catch."
Niara is building a security analytics platform that collects different forms of data, he said, adding that the system observes and monitors user behavior over time to build a profile of normal activity. "If an attacker has stolen a user's credentials, we're counting on the fact that the attacker's intent inside the network is going to be different and, therefore, Niara can see the deviation," Ramachandran said.
The basic assumption that Niara is making is that humans will behave in predictable ways. The Niara platform has some machine learning and intelligence capabilities that help identify potential outliers to normal user behavior.
Many organizations have security information and event management (SIEM) systems that collect logs about system activity. SIEM information can also be input into the Niara model, Ramachandran said.
Niara is making use of big data techniques and Hadoop. "The core intellectual property of Niara is in the collection, storage and analysis of the data," Ramachandran said. "We have been at work for 16 months building the platform."
While some of the components in Niara's platform are open-source, the big challenge has been in aligning an entire application stack to be able to handle the scale that is needed, Ramachandran said. "You have to be very smart about how you process data and how you move it around," Ramachandran said.
Since Niara is still in its stealth mode, Ramachandran declined to provide specific details about the analytics engine used in Niara. However, he noted that Niara uses multiple techniques, including discrete and behavioral analytics, and makes use of machine learning functionality.
The plan for Niara's platform is to have both cloud as well as on-premises deployment capabilities. "We have built a very flexible platform, as the reality is that there is some reluctance for organizations about moving sensitive data to the cloud," Ramachandran said.
While the Niara platform aims to help find sophisticated attacks, in the first version of the product, those attacks will not be automatically blocked. However, automated remediation capabilities are on Niara's product road map for future releases.
"Customers are generally reluctant to take that automated step until they understand the technology and have the confidence to take remediation actions in an automated fashion," Ramachandran said.
Sean Michael Kerner is a senior editor at eWEEK and InternetNews.com. Follow him on Twitter @TechJournalist.