Both announcements come less than two weeks after the company rolled out its new Fabric Connectors, which help automate security operations and policies through one-click integrations with partners including Amazon Web Services (AWS), Cisco ACI, Google Cloud Platform, Microsoft Azure, and VMware NSX.
Bradford Networks is a network access control (NAC) vendor based in New Hampshire. It was founded in 1999 and has raised $16 million to date, according to Crunchbase.
Bradford previously partnered with Fortinet through its Fabric-Ready Partners program, which integrates other security technologies with Fortinet’s Security Fabric. Partners join across various API integration points, and this integrated platform enables security management across cloud, virtual, and software-defined environments.
The acquisition will strengthen Fortinet’s IoT security offerings, said John Maddison, SVP of products and solutions at Fortinet.
“Our goal is to build a Security Fabric from IoT all the way into the cloud,” Maddison said. “We have good visibility at the access point, switching and gateways, but we also have a lot of devices where we didn’t have a mechanism to identify them. Bradford Networks really allows us to focus in on the NAC marketplace and also IoT security. It brings those two markets together, and it gives us that extra visibility on the end points without having to put devices on every single endpoint.”
Adding ML to WAF
Fortinet also added artificial-intelligence-based machine learning capabilities to its FortiWeb WAF. This makes its software release 6.0 the only major WAF to use machine learning for behavioral-based threat detection in web applications, the company claims.
A web application firewall protects public and internal web applications deployed on premises and in the cloud. Companies deploy WAFs in front of servers to protect applications and APIs against external and internal attacks.
Fortinet sells its WAF as a hardware device, software-as-a-service, and virtual appliance in Amazon Web Services, Microsoft Azure, and soon Google Cloud, according to Maddison. “We’re seeing a big uptake in cloud WAFs,” he added.
The WAF market is growing, according to Gartner, which says cloud-based WAF services are driving adoption. By 2020, stand-alone WAF hardware appliances will represent less than 20 percent of new WAF deployments, down from 40 percent today, the analyst group says. And by 2020, more than 50 percent of public-facing web applications will be protected by cloud-based WAF service platforms, combining CDN, DDoS protection, bot mitigation and WAF, up from less than 20 percent today.
WAFs typically use application learning (AL) for anomaly and threat detection, but this technology’s limitations lead to false positives, which require a significant amount of time to manage for already time-strapped security teams.
Application Leaning Vs. Machine Learning
“One of the issues with cloud WAFs is you traditionally have to do a lot of tuning, setting up signatures and making sure you can solve the problems,” Maddison said. “But the more you try to stop stuff, the more false positives you get. It’s an ideal application for machine learning.”
Unlike AL, which uses a one-layer approach to detect anomalies based on matching inputs to what it has observed and treating every variation as a threat, FortiWeb’s now uses a two-layer approach of machine learning and statistical probabilities to detect anomalies and threats separately. The first layer builds the mathematical model for each learned parameter and then triggers anomalies for abnormal requests. The second will then verify if the anomaly is an actual threat or a false positive.
These new machine learning capabilities allow Fortinet’s WAF to provide almost 100 percent application threat detection accuracy. It also requires no additional resources to deploy or fine-tune settings, Maddison said. “Within a couple of days, it learns what it needs to stop and what it needs to let through, reducing false positives to almost zero,” he added.
The WAF also integrates with Fortinet’s Security Fabric.