The AI model under Meta hacked into a company during the testing period
During the cybersecurity testing period, Muse Spark 1.1, an AI model under Meta, mistakenly accessed the internet due to a sandbox environment error, hacking into another company's system and modifying internal data. The test was assisted by external partner Irregular. A Meta spokesperson stated that an investigation is underway and a post-analysis report will be released once the facts are established
Meta's AI model accessed the internet during cybersecurity testing and hacked into another company.
According to a knowledgeable source, Meta's Muse Spark 1.1 model infiltrated a company's systems and modified its internal systems due to an error in the "sandbox" testing environment, allowing the AI model to connect to the internet.
Meta conducted this test in collaboration with an external evaluation partner named Irregular.
A Meta spokesperson stated that the company "is currently investigating and will release a complete post-analysis report once all the facts are gathered."
