Information-Sharing

The Frontier Model Forum (FMF) was established with a mission to create a secure information-sharing framework between industry, civil society, and government. 

In March 2025, the member firms of the FMF signed a first-of-its-kind agreement to facilitate information-sharing about vulnerabilities, threats, and capabilities of concern unique to frontier AI. 

At this stage, our information-sharing covers the following three key categories:

• Vulnerabilities, weaknesses, and exploitable flaws. Vulnerabilities, weaknesses or exploitable flaws may compromise the safety, security, or intended functionality of frontier AI models. Examples may include jailbreaks, adversarial inputs, data poisoning, or other attempts to bypass model safeguards.

• Threats. Threats to frontier AI comprise threats directed to the unauthorized access or manipulation of frontier AI models. Examples may include potential threat actors, attack vectors, or cyber-threat indicators. 

• Capabilities of Concern. Capabilities of concern refer to frontier AI capabilities that have the potential to cause large-scale harm to society. Examples may include capabilities related to the development of chemical, biological, radiological, and nuclear (CBRN) threats, offensive cybersecurity attacks, and model autonomy. 

The FMF aims to refine its information-sharing function over time in a way that supports collaboration with the broader frontier AI ecosystem.