Gurucul extends behavior based security analytics to entire IT stack
Gurucul, a leader in behavior based security and fraud analytics technology, announced a new version of its Gurucul Risk Analytics (GRA) platform, which extends behavior based security analytics with pre-built machine learning models that span the entire IT stack.
GRA version 7.0 unifies siloed analytics to provide real-time anomaly and risk detection across enterprise and cloud platforms/applications, networks, mobile endpoints, IoT devices, medical devices, business applications and more. Gurucul goes beyond SIEM’s capabilities, including the ability to automate security controls such as risk and behavior based step-up authentication and preventative DLP enforcement in high risk situations.
The new version of GRA also provides a new streamlined user experience that includes an open and flexible framework for personalizing widget-driven dashboards with a wide range of visualizations and canvas-based components to view, modify or build new behavior and threat models using Gurucul Studio™. Gurucul GRA is available as a cloud service, and can be deployed in the cloud, on-premises data centers, or hybrid environments.
According to the recent Forrester Wave: Security Analytics Platforms report, “enterprises looking for a robust security analytics tool with strong SUBA [security user behavior analytics] and data protection should consider Gurucul”.
Broadest & deepest security analytics platform
Digital transformation is expanding the traditional enterprise attack surface to include a variety of new devices that are interconnected and use off the shelf operating systems including IoT devices, medical equipment, POS systems, etc. Detecting malicious activity in these distributed and traffic intensive environments is beyond the capabilities of siloed, rule and pattern-based monitoring solutions.
Gurucul offers a real-time behavior analytics platform that uses open choice, “no cost” Big Data to collect high-frequency events / transactions and contextual metadata from the entire IT stack and run machine learning models that detect and risk-score suspicious activity.
“For effective risk mitigation, a security analytics platform must be able to span the entire IT footprint of an organization and provide an open framework to create user defined entities, modify existing machine learning models and trigger risk-response actions in real-time,” said Nilesh Dherange, CTO of Gurucul. “Just as we were the first to extend behavior analytics from on-premises to the Cloud, Gurucul UEBA is the only solution helping customers with risk detection and scoring to the extended enterprise of mobile, IoT, PoS, medical and other entities.”
Custom dashboards & visualization
To address specific business functions and use case requirements, Gurucul Risk Analytics now provides out-of-the-box dashboards for UEBA, fraud analytics, cloud analytics, access analytics, network analytics, as well as customizable business roles including SOC Analyst, Network Analyst, DLP Analyst, Privacy Officer, Data Scientist, etc. Each dashboard can be easily customized using drag and drop widgets to provide data and visualizations tailored to each user’s needs and preferences.
Largest ML model library and open analytics framework
To detect advanced threats from external attackers and malicious insiders such as fraud, data exfiltration, and account compromise, Gurucul now has more than 1000 pre-packaged machine learning models. These include unsupervised, supervised and deep learning algorithms, as well as versions that are pre-tuned to predict and detect specific types of threats and for industry use cases such as finance, healthcare and retail.
In addition, organizations can easily customize existing models or build their own using Gurucul STUDIO, which provides canvas-based drag-and-drop components for analysts, data scientists or administrators to design behavior, threat and risk models without having to write code. STUDIO also provides a centralized analytics platform and SDKs for data scientists to build and import their own custom models.
Gurucul’s vast library of ML models also enables organizations to implement model-driven security to automate responses to high risk activity and reduce security “friction”. For example, powered by ML models, behavioral risk based authentication can improve the end user experience by doing away with passwords while increasing security.
This continuous, model-driven authentication process can make in-the-moment decisions about a users’ confirmed identity before allowing the session or requested action to continue. Authentication and authorization are no longer a singular event, but an engaged process that persists throughout the user’s experience in the environment.