NSS Labs Names Keysight Lead Partner for AI Protection Systems Testing Initiative

NSS Labs said Keysight Technologies joined its Artificial Intelligence (AI) Protection Systems (AIPS) security testing initiative as lead partner. The effort will support an independent evaluation program for technologies meant to govern and protect AI deployments, using a structured testing methodology.

NSS Labs framed the work around a gap in standardized, independent validation for AI security controls, including AI guardrails, AI firewalls, or AI runtime protection systems. The program is intended to benchmark how these systems perform against real-world threats while keeping policy enforcement and operational integrity in scope.

NSS Labs described an AIPS methodology that evaluates products across seven dimensions of AI security: malicious input and prompt attacks, output risks and sensitive data exposure, system resilience under adversarial conditions, policy enforcement accuracy, agentic AI and tool invocation security, observability and audit capabilities, and performance and scalability impact. It said the approach includes hundreds of thousands of test case executions using multiple attack samples and variations, including prompt injection attempts, jailbreak techniques, obfuscated prompts, sensitive data extraction attempts, exploit generation requests, Retrieval Augmented Generation (RAG) poisoning attacks, Application Programming Interface (API) privilege escalation attempts, and agent tool misuse scenarios.

Vikram Phatak, CEO of NSS Labs, said, “AI is rapidly becoming core infrastructure for the digital economy, and with that comes an urgent need for independent validation of the technologies designed to protect it,” said Vikram Phatak, CEO of NSS Labs. “With Keysight joining us as lead partner, we are bringing together our deep expertise in testing along with Keysight’s global innovation solutions that will help the industry understand how well AI protection systems actually perform against real-world threats.” Random Access Memory (RAM) Periakaruppan, Vice President and General Manager, Network Test & Security at Keysight, said, “AI is quickly becoming foundational infrastructure, and trust in these systems must be earned through transparent, independent validation,” said RAM Periakaruppan, Vice President and General Manager, Network Test & Security at Keysight. “Keysight’s strength in building scalable, real-world test environments and generating actionable performance insights positions us to help shape how AI security is measured. We’re proud to partner with NSS Labs to advance a more resilient and trustworthy AI ecosystem.” NSS Labs said it is accepting feedback on the methodology from enterprises and security vendors, and it plans to publish the AIPS methodology in April.