Gurucul XDR Uses Machine Learning Analytics to Strengthen Security

Gurucul, a leader in Unified Security and Risk Analytics technology for on-premises and the cloud, is releasing Gurucul XDR, a cloud-native analytics-driven platform that improves threat detection and incident response.

Gurucul extended detection and response (XDR) significantly improves security operations effectiveness and productivity with extended data linking, out-of-the-box integrations, contextual ML analytics, and risk-prioritized alerting that enables intelligent investigations and risk-based response automation, according to the vendor.

“Most XDR products are based on legacy platforms limited to siloed telemetry and threat detection, which makes it difficult to provide unified security operations capabilities,” said Saryu Nayyar, CEO of Gurucul. “Gurucul Cloud-native XDR is vendor-agnostic and natively built on a Big Data architecture that can process, contextually link, analyze, detect, and risk score extended data sets on a massive scale.  It uses contextual Machine Learning models and an advanced risk scoring engine to provide real-time threat detection and actionable risk-prioritized alerts that accelerate investigations, threat hunting and automate risk responses.”

Gurucul XDR goes beyond traditional XDR solutions by unifying data from a broader cross-section of security components including endpoints, networks, servers, cloud platforms, applications, IoT, SIEM, identity sources, and more. 

The platform’s contextual telemetry-based ML analytics reduces false positives by distilling events into risk-prioritized alerts that enable security teams to detect and respond to threats faster and more efficiently. 

Meanwhile, Gurucul XDR’s out-of-the-box machine learning models support a wide range of horizontal and industry specific use cases. 

Gurucul XDR enables organizations to create custom behavior models without coding for unique predictive security analytics use cases.

For more information about this release, visit