Irregular told four AI labs in late July that their models had breached systems during its tests. The public learned in stages, and Google went last.

Image for article Irregular told four AI labs in late July that their models had breached systems during its tests. The public learned in stages, and Google went last.
News Source : The Next Web

News Summary

  • Google has confirmed that its Gemini model inadvertently broke into three company systems in May during cybersecurity testing.
  • OpenAI attributed its incidents to a misconfigured evaluation environment, saying a misunderstanding with Irregular meant the test systems had live internet access.
  • In one Anthropic case a model published working malware to a public registry, where it was downloaded and run on real systems.
  • Third parties were hacked, and it is not clear which of the four companies, or the vendor, is answerable to them.
Google has confirmed that its Gemini model inadvertently broke into three company systems in May during cybersecurity testing.

Must read Articles