Third-party cyber evaluations involving OpenAI models

PUBLISHER ARTICLE PREVIEW

From the original article

Independent testing plays an important role in helping us validate and further understand risks before deployment. Some cyber evaluations intentionally use custom configurations, including lowered safeguards to measure underlying capability—not how models ordinarily behave in publicly available deployments.

During recent evaluations, two external testing partners identified incidents in which testing configurations and controls combined with the advancing capabilities of the recent models allowed for model activity to extend beyond their intended testing boundaries. The incidents underscore the importance of collaborating across the industry and with third party evaluators to evolve the standards for testing environments and practices as models become more capable.

Editor’s Note: These are separate from the Hugging Face security incident, and we will continue to share updates on the Hugging Face incident here.

The new incidents involved OpenAI models accessing the public internet during third-party cyber evaluations, under specific conditions and reduced-safeguard configurations that did not reflect ordinary deployment. The incidents included:

UK AISI, the UK government’s AI Security Institute, was running cyber-range evaluations with internet access intentionally enabled so agents could find their own tools and operate under conditions closer to a real attacker, and with cyber classifiers disabled to measure underlying capability. You can read their blog here.⁠

Irregular, one of our external cybersecurity testing partners, was running Capture-the-Flag-style evaluations intended to be isolated from the internet, but a testing-environment misconfiguration allowed models to access the public internet.

Below, we summarize what happened, the testing conditions that enabled the activity, the steps taken to contain it, and what we’re doing to ensure independent labs can continue to rigorously and safely evaluate increasingly capable models.

These incidents point to the same broader challenge we described in our recent post about the Hugging Face incident: as model capabilities advance, the security and safety systems around models need to advance too. That includes both the environments used to develop models, and also the environments that labs and independent partners use to evaluate them.

In the coming weeks, we will review our own approach to third-party testing, including how we identify higher-risk evaluations, agree on scope, assess requests to enable internet access or lowered safeguards, set expectations for isolation, credential