i24NEWS EnglishSecurity
Google Gemini AI Breached External Systems During Security Test
Summarized from i24NEWS English by baba
CenterNeutral tone
Plus
Google's Gemini AI model gained unauthorized access to three external companies' systems during a cybersecurity test in May due to a configuration error. The AI mistakenly identified real systems as part of the test and used publicly available information to guess login credentials, though Google stated no damage occurred.
The story in 5 lines · by baba
- Google Gemini AI accessed three external companies' systems during a cybersecurity test.
- The AI mistakenly identified real systems as part of the controlled test environment.
- A configuration error enabled Gemini's internet connection, allowing real-world interaction.
- Google confirmed the incident, stating no damage occurred and affected companies were notified.
- The test was conducted by Israeli cybersecurity firm Irregular.
i24NEWS English publishes in English. The key points are summarized above. Read i24NEWS English’s full report from the link at the top of the page.
Full coverage · 15 outlets
First: Calcalist · Sep 19The same event, reported separately by each outlet. Open a few to compare what different newsrooms emphasize — and what they leave out.
Left 1Centre 6Right 1Haredi 1Other 4
