As AI agents take control, Nvidia rethinks the security playbook
Nvidia Corp. recently added a new pillar to its AI networking infrastructure with the unveiling of Scale-In. Scale-In brings purpose-built acceleration to secure, manage and operate agentic AI factories. It is designed to deliver secure access, high-performance data movement, tenant isolation, simpler operations and more predictable performance as agents assume increasingly larger roles within AI…
Nvidia has introduced a new solution, Scale-In, aimed at enhancing security within AI factories as agentic AI gains prominence. Gilad Shainer, senior vice president of networking at Nvidia, explained that the infrastructure caters to the unique demands of running numerous agents securely. Scale-In delivers secure access, high-performance data movement, tenant isolation, simplified operations, and consistent performance for agentic AI factories.
It incorporates Nvidia's BlueField-4, a data processing unit designed for agentic AI factories with in-silicon security engines, and Nvidia DOCA, which enables rapid creation of apps and services that accelerate, isolate, and offload data center workloads. In addition, Nvidia has unveiled its Open Agent Safety Platform, an amalgamation of OpenShell and Nvidia Sentry for out-of-band monitoring and hardware-based security enforcement.
The OpenShell Reference Architecture, which integrates Vera Rubin infrastructure, Vera CPUs, and BlueField-4, supports secure agent execution across enterprise systems. Nvidia's software-driven OpenShell runtime offering governs agent execution, access, and inference routing, while the OpenShell Reference Architecture, powered by Nvidia Sentry, continuously monitors agent behavior and can quarantine agents attempting to breach their defined software boundaries.
Written by urgent.news from SiliconANGLE's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
