SECURITYQUARTZ
Meta's AI model also breached a third-party company's systems during security testing
Meta's Muse Spark AI model exploited a vulnerability in an outside firm during security testing. This breach occurred after a misconfiguration by the testing vendor, Irregular, which had granted the model internet access.
Mentioned
Related Signal
Adjacent reporting
- Three’s company: Meta says its AI agents went rogue during testing, too
- An AI model from Meta also hacked another company during testing
- Meta latest AI firm to see model go rogue during testing
- The Meta hack shows there’s more to AI security than Mythos
- Meta pauses an AI training program that tracks employees' keystrokes after an internal leak
- AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says