Meta AI model accessed internet and hacked another company during testing

technology artificial intelligence cybersecurity

Meta revealed Wednesday that one of its artificial intelligence models hacked another organization during cybersecurity testing. The incident occurred after an error by its testing partner gave the model unintended internet access, allowing it to breach an outside service's systems.

Meta is the latest of several major developers to report such an incident. This follows a disclosure from Anthropic, which stated that some of its models hacked three companies, and OpenAI, which revealed that an AI agent breached the startup Hugging Face.

These events mark the third time in recent weeks that an AI model has improperly accessed a third-party company. The growing list of breaches has raised cybersecurity concerns and escalated worries about the control companies have over their technology.

Meta says its AI model breached a third-party company during testing

cbsnews.com

Meta says AI model accessed the internet and hacked another firm

bbc.co.uk

Meta says its AI model hacked into another company during testing

theguardian.com

Meta’s AI model follows rivals in revealing hacks of outside systems

aljazeera.com

Meta AI model hacks another company during testing

straitstimes.com

Meta’s AI model hacks another company during cybersecurity testing

theglobeandmail.com

Meta AI Model Accessed Internet, Hacked Outside Firm in Testing

bloomberg.com