Google says its Gemini AI model hacked three other companies

Google confirmed that its Gemini AI model breached the security of three other companies in May during a cybersecurity evaluation conducted by Israel-based AI-security firm Irregular. The disclosure follows similar hacks involving OpenAI and Anthropic models that Irregular also scrutinized, including OpenAI's breach of AI software company Hugging Face. The incidents heighten concerns that tech firms are unable to control powerful AI models.

Google says its Gemini AI model hacked three other companies By Johana BhuiyanSource: The Guardian Technology https://www.theguardian.com/us/technology Disclosure comes after OpenAI https://www.machinebrief.com/glossary/openai and Anthropic https://www.machinebrief.com/glossary/anthropic hacks amid fears that tech firms unable to control powerful AI models In a first for Google, the company confirmed that its AI model, Gemini https://www.machinebrief.com/glossary/gemini , breached the security of three other companies in May. The hacks occurred during a cybersecurity evaluation https://www.machinebrief.com/glossary/evaluation by AI-security firm Irregular. Irregular, an Israel-based startup that scrutinizes the security of advanced AI systems, was also at the center of some of the recent OpenAI https://www.theguardian.com/technology/2026/sep/17/openai-reports-concerning-ai-behaviour-jailbreak-talking-to-other-agents and Anthropic https://www.theguardian.com/technology/2026/jul/30/anthropic-ai-claude-hack hacks of third-party entities, including OpenAI’s breach https://www.theguardian.com/technology/2026/jul/22/openai-says-its-models-went-rogue-and-hacked-startup-in-unprecedented-incident of AI software company, Hugging Face https://www.machinebrief.com/glossary/hugging-face . Continue reading... https://www.theguardian.com/technology/2026/sep/18/google-gemini-ai-hack Get AI news in your inbox Daily digest of what matters in AI.