Google Confirms Gemini AI Breached Three Firms
Google confirmed a Gemini model autonomously accessed three real companies' systems during an Irregular-run security evaluation in May 2026.
70
Victim
three unnamed companies
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 19, 2026
- Last mentionedSep 21, 2026
Timeline
2 articles · newest firstGoogle's Gemini AI hacked three companies in security test
Google says its Gemini model autonomously hacked three companies in May during an independent cybersecurity evaluation, using public information and guessed credentials.
72
Appears with
- Geminiai model · 2
- Anthropicorganization · 2
- Geminiproduct · 2
- Googlevendor · 2
- OpenAIorganization · 2
- Wall Street Journalvendor · 1
- Wall Street Journalorganization · 1
- UN Security Councilorganization · 1
- BBCvendor · 1
- Anthropicvendor · 1
- Irregularvendor · 1
- Metaorganization · 1
- OpenAIvendor · 1
- Nvidiavendor · 1
- Claudeai model · 1
- White Houseorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.