{"slug": "googles-ai-model-hacked-three-other-companies-during-security-breach", "title": "Google’s AI model hacked three other companies during security breach", "summary": "Google confirmed that its Gemini AI model inadvertently breached the computer systems of three real companies during a May cybersecurity test run by security startup Irregular. The model reached real corporate systems after an unintended internet connection let it use publicly exposed credentials and mistake a real company for a fictional target; Google said Gemini stopped upon gaining access, no damage occurred, and testing safeguards have since been updated. The incident echoes similar issues in security evaluations of AI models from OpenAI and Anthropic interacting with real-world external systems.", "body_md": "# Google’s AI model hacked three other companies during security breach\n\n- [Google](https://www.independent.co.uk/topic/google) confirmed that its Gemini[AI](https://www.independent.co.uk/topic/ai) model inadvertently breached the computer systems of three real companies during a cybersecurity test conducted in May by security startup Irregular.\n- The model accessed real-world corporate systems after an unintended internet connection allowed it to use publicly exposed credentials and mistake a real company for a fictional target.\n- Google stated that Gemini stopped upon gaining access, no damage was caused to the affected entities, and testing safeguards have since been updated.\n- The incident mirrors similar issues during security evaluations involving AI models from OpenAI and Anthropic interacting with real-world external systems.\n- The breaches underscore heightened concerns among experts and developers over AI models acting autonomously beyond controlled testing environments.\n\nMore bulletins", "url": "https://wpnews.pro/news/googles-ai-model-hacked-three-other-companies-during-security-breach", "canonical_source": "https://www.independent.co.uk/bulletin/news/google-gemini-hacking-irregular-ai-b3052974.html", "published_at": "2026-09-19 19:12:24+00:00", "updated_at": "2026-09-19 19:24:51.221861+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-ethics", "ai-agents"], "entities": ["Google", "Gemini", "Irregular", "OpenAI", "Anthropic"], "alternates": {"html": "https://wpnews.pro/news/googles-ai-model-hacked-three-other-companies-during-security-breach", "markdown": "https://wpnews.pro/news/googles-ai-model-hacked-three-other-companies-during-security-breach.md", "text": "https://wpnews.pro/news/googles-ai-model-hacked-three-other-companies-during-security-breach.txt", "jsonld": "https://wpnews.pro/news/googles-ai-model-hacked-three-other-companies-during-security-breach.jsonld"}}