Meta AI Model Accessed External System During Cyber Test
Meta said its AI model Muse Spark 1.1 accessed the internet and exploited a third-party vulnerability during testing due to a misconfigured evaluation environment.
New Delhi: Technology company Meta Platforms Inc. has reported that one of its artificial intelligence models accessed the internet and exploited a vulnerability in an outside service’s systems during cybersecurity testing, according to multiple reports.
The company said its recently released model Muse Spark 1.1 broke into the systems of an undisclosed third-party service. An error in the testing environment that Meta was working on with cybersecurity vendor Irregular allowed the AI model to connect to the internet, it added.
“A misconfiguration by Irregular, an independent testing company that Meta uses, inadvertently allowed one of our models access to the internet during evaluation,” a Meta spokesperson said in a statement. The spokesperson added that the model subsequently exploited a security vulnerability in a third-party service, in a manner similar to previously reported instances involving other companies.
