NVIDIA this week unveiled Morpheus, a cloud-native application framework designed to help cybersecurity providers analyze more data without sacrificing performance.
According to NVIDIA, Morpheus leverages machine learning to identify anomalies and threats — such as phishing, data leaks and malware — through real-time inspection of all IP traffic in an organization’s data centers.
Morpheus works with NVIDIA’s BlueField data processing units (DPUs), a powerful processor designed specifically for data centers.
“Morpheus, when combined with BlueField DPUs, enables every compute node in the network to serve as a cyber-defense sensor at the edge, letting organizations analyze every packet with line-rate speed without data replication,” NVIDIA said. “In contrast, traditional AI security tools typically sample around five percent of network traffic data, leading to threat-detection algorithms based on incomplete models.”
Morpheus provides pre-trained AI capabilities, but the company says developers can also create their own skills.
NVIDIA is already working with cybersecurity, hardware and software companies to optimize and integrate their solutions with the Morpheus framework. The list currently includes ARIA Cybersecurity, Cloudflare, Fortinet, F5 Networks, Splunk, Guardicore, Canonical, Red Hat and VMware.
Related: NVIDIA Ships Patches for High-Severity Security Flaws
Related: NVIDIA Patches AMI BMC Vulnerabilities Impacting Several Major Vendors
Related: NVIDIA Patches Code Execution Flaws in GeForce Experience
