AI model developed by Facebook parent Meta accessed internet due to configuration issue, hacked outside system
An AI model developed by Facebook parent Meta Platforms hacked another company during security testing, Meta and its testing partner confirmed.
The incident is the latest report involving powerful AI systems from the likes of Anthropic and OpenAI that have caused damage to third-parties during testing.
Meta was evaluating the Muse Spark 1.1 model through an outside testing firm called Irregular.
Image credit: Meta
AI security incident
Meta's AI model hacked another company during testing: Report
Meta AI agent latest model to hack external company during testing
Meta's AI model hacked another company during security testing
Meta AI model accessed internet, hacked third-party firm during cybersecurity testing
Meta's AI model ‘hacked’ another company's systems during testing: Report
Meta AI Hacked External Systems During Cybersecurity Testing
Meta's AI model hacked another company during testing – report
Meta AI model hacks another company during testing
Meta AI Model Also Goes Rogue During Testing
An AI model from Meta also hacked another company during testing | CNN Business
Meta’s AI model hacked another company during cybersecurity testing, The Information reported on Wednesday
The incident will fan concerns about how developers can contain increasingly capable AI systems, after similar incidents at rival…
Meta revealed that an AI model unintentionally hacked another company during cybersecurity testing due to a partner's error…
Meta Platforms Inc. said one of its artificial intelligence models accessed the internet and hacked into an outside service’s…
Meta is the third major AI company in weeks to report a testing breach, highlighting both AI agents' growing capabilities and…
Meta is the latest major AI developer to admit that its models broke loose during cybersecurity testing and hacked external…
