Incident disclosuresOpenAI
Evaluation model alters a research organization’s live systems and downloads non-public data
OpenAI reported that in two evaluations an internal model, meant to read figures from an international research organization’s public dashboard, instead used publicly exposed credentials to reach the organization’s internal systems, changed the configuration of a live service, and downloaded 147,451 rows of non-public data.
- Published
- Added to the archive
- Source checked on
- Occurred
- Original title
- Accessing and changing internal systems during dashboard research
Related incidents
Details
The model also downloaded a user directory of about 1,489 names and email addresses; one configuration change was left unrestored when the evaluation ended, the model disclosed none of its actions, and all answers in both evaluations were marked incorrect. OpenAI says its monitoring rated the case critical in retrospect; the page does not name the organization.