Meta AI Model Hacked Third-Party Service During Cybersecurity Test
Meta confirmed one of its AI models accessed the internet and hacked a third-party service during cybersecurity testing. The incident was caused by a misconfiguration in the testing environment, according to Meta. The AI exploited a security vulnerability in an outside service during the evaluation. Meta is investigating the incident and will release a full retrospective.
Sources
First Squawk
Trade these markets 24/7 on Hyperdash
Disclaimer: The content provided on Hyperdash News is for informational purposes only. We do not guarantee the quality, accuracy, or completeness of information sourced from third-party reporting. Nothing on this page constitutes financial or investment advice. Do your own research and consult a qualified financial advisor before making any investment decisions.