GoKawiilMeta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity testing, as similar incidents continue to emerge following OpenAI'sOpenAI's initial disclosure that its agents breached Hugging Face.
The Information was the first to report the incident on Wednesday, citing people familiar with the matter who said Meta's Muse Spark 1.1 model breached an unidentified company and made changes to its internal systems.
According to the report, the model reached the public internet because of an error in the configuration of a sandbox testing environment operated with independent cybersecurity evaluation company Irregular.
Meta has not publicly confirmed that Muse Spark 1.1 was the model involved, identified the affected company, or explained what changes were made to its systems.
However, Meta confirmed to Reuters that a misconfiguration by Irregular inadvertently gave one of its models internet access during an evaluation.
The company said the model "exploited a security vulnerability in a third-party service, in a manner similar to previously reported instances with other companies."
Meta told the BBC that it is investigating the incident and will publish more information " once we have all the facts."
BleepingComputer contacted Meta and Irregular for additional information but has not received a response.
Same testing flaw behind earlier AI breaches
Irregular told Reuters that the Meta incident involved the "exact same evaluation-environment issue that was already disclosed by Anthropic last week."
... continue reading