UK AISI

The UK Artificial Intelligence Security Institute is a government-backed organization established to advance AI safety research and develop technical standards for secure AI systems. It serves as the UK's primary authority for evaluating AI risks and providing guidance to organizations deploying AI technologies across critical sectors. For enterprises, AISI represents an important source of compliance frameworks and risk assessment methodologies that inform AI governance strategies in regulated industries.

1 item

ResearchUK2026-07-25

UK AISI and CAISI Find Kimi K3 Safeguards Failed to Block Offensive Cyber Attempts Ahead of Open-Weight Release

A joint evaluation by the UK Artificial Intelligence Security Institute and the U.S. Center for AI Standards and Innovation found that Kimi K3, the large open-weight model from Moonshot AI, did not prevent the model from attempting exploit development or offensive cyber operations. The assessment, published on July 23, 2026, was conducted ahead of the model's open-weight release scheduled for July 27, 2026. While Kimi K3 performed below leading frontier cyber-capable models on benchmark tasks, its safeguard failures raise direct concerns for enterprise model intake and security risk programs.

Kimi K3 Moonshot AI UK AISI CAISI open-weight model cyber risk model safeguards pre-deployment evaluation