NIST Introduces National Generative AI Testing Program

The National Institute of Standards and Technology (NIST) is moving toward establishing a more standardized national approach to AI safety. The government agency has announced the launch of NIST GenAI, described as an "evaluation program to support research in Generative AI technologies."

The launch comes six months after the Biden White House signed an Executive Order requiring LLM makers to implement guardrails around AI technologies that protect the privacy and security of consumer data. For instance, the order mandated the development of "standards, tools, and tests to help ensure that AI systems are safe, secure, and trustworthy," and of "standards and best practices for detecting AI-generated content and authenticating official content."

The NIST GenAI program is part of the department's effort to address those mandates.

A companion NIST program, dubbed Aria, is set to launch soon. Aria's stated goal is "to advance measurement science for safe and trustworthy AI."

In a press release Monday, the U.S. Department of Commerce, of which NIST is part, described the GenAI program as a platform to "evaluate and measure generative AI technologies."

"The NIST GenAI program will issue a series of challenge problems designed to evaluate and measure the capabilities and limitations of generative AI technologies," said the agency. "These evaluations will be used to identify strategies to promote information integrity and guide the safe and responsible use of digital content."

The first of these challenges aims to evaluate the efficacy of text-to-text (T2T) AI models -- those that generate human-like text ("generators"), as well as those that purport to detect AI-generated text ("discriminators"). Findings from the challenge will help guide the NIST's eventual recommendations to LLM makers for how to convey the provenance of content made using their AI systems. This is how NIST describes the challenge in its Overview page:

NIST GenAI T2T is an evaluation series that supports research in Generative AI Text-to-Text modality. Which generative AI models are capable of producing synthetic content that can deceive the best discriminators as well as humans? The performance of generative AI models can be measured by (a) humans and (b) discriminative AI models. To evaluate the "best" generative AI models, we need the most competent humans and discriminators. The most proficient discriminators are those that possess the highest accuracy in detecting the "best" generative AI models. Therefore, it is crucial to evaluate both generative AI models (generators) and discriminative AI models (discriminators).

The challenge is open to academics, researchers and LLM makers; those interested can read the participation guidelines here. A similar challenge to evaluate text-to-image models is set to start soon.

Besides the GenAI program launch, NIST this week released preliminary versions of four papers about the secure development and implementation of AI. These papers, which are described as "initial drafts," are as follows:

Each draft is still subject to change based on public input. The NIST is accepting feedback for each publication until June 2, and plans to publish final versions published "later this year."

About the Author

Gladys Rama (@GladysRama3) is the editorial director of Converge360.

Featured

  • students using digital devices, surrounded by abstract AI motifs and soft geometric design

    Ed Tech Startup Kira Launches AI-Native Learning Platform

    A new K-12 learning platform aims to bring personalized education to every student. Kira, one of the latest ed tech ventures from Andrew Ng, former director of Stanford's AI Lab and co-founder of Coursera and DeepLearning.AI, "integrates artificial intelligence directly into every educational workflow — from lesson planning and instruction to grading, intervention, and reporting," according to a news announcement.

  • glowing AI text box emerges from a keyboard on a desk, surrounded by floating padlocks, warning icons, and fragmented shields

    1 in 10 AI Prompts Could Expose Sensitive Data

    A recent study from data protection startup Harmonic Security found that nearly one in 10 prompts used by business users when interacting with generative AI tools may inadvertently disclose sensitive data.

  • modern school building surrounded by a glowing digital shield and floating lock icons

    CoSN Launches Campaign Advocating for Congressional Support for K-12 Cybersecurity

    CoSN, the professional association for K-12 ed tech leaders, has launched a national advocacy campaign urging Congress to maintain federal support for cybersecurity assistance in K-12 education.

  • chart with ascending bars and two silhouetted figures observing it, set against a light background with blue and purple tones

    Report: Enterprises Are Embracing Agentic AI

    According to a new report from SnapLogic, 50% of enterprises are already deploying AI agents, and another 32% plan to do so within the next 12 months..