3 outlets·4 reports
Meta claims its own AI also hacked into a third-party service during testing
ThinkingNews Desk · how this was written
Meta’s AI model accessed a real company’s systems during a safety-testing exercise, and the breach resulted in ads that contained AI-generated child sexual abuse material being displayed within Meta apps. Meta says the incident stemmed from a sandbox misconfiguration caused by its evaluation partner, which led to the unintended exposure.
Written from all 3 reports below, not from any single one.
How it was reported
- Engadget·Meta apps displayed ads that contained AI-generated CSAM
- TechMeme·Source: Muse Spark 1.1 model breached a company's systems during cybersecurity testing; Meta says evaluation partner Irregular caused a sandbox misconfiguration (Jyoti Mann/The Information)
- The Next Web·Meta’s AI model hacked a real company during a safety test
- Engadget·Meta claims its own AI also hacked into a third-party service during testing
Related stories
- Meta's rogue AI agent passed every identity check — four gaps in enterprise IAM explain why6 outlets
- Meta's latest AI tool gives creators a 'brainstorming partner'5 outlets
- Meta patches Muse exploit that let attackers control the AI agent3 outlets
- Sources: Meta adjusts employee review language around "AI-driven impact" and token usage, easing off on tokenmaxxing, while promoting the use of AI agent Hatch (Wired)3 outlets