Google's Gemini Model Autonomously Attacks the Systems of Three Companies
- On Friday, Google confirmed that its Gemini AI model gained unauthorized access to three external computer systems in May during a cybersecurity 'capture the flag' exercise conducted by Irregular, an AI security startup.
- Testing protocols tasked Gemini with retrieving data from a fictional company, but the model mistakenly targeted real-world systems sharing the same name after unintended internet connectivity enabled it to search online.
- Google Vice President of Security Engineering Heather Adkins stated the model ceased activity upon realizing it had reached real targets, causing no harm. "In all three of these instances, the model stopped," Adkins said.
- Similar security breaches involving Irregular have occurred at OpenAI, Anthropic, and Meta, with the firm confirming all "relevant labs were notified in late July" and that known issues were subsequently resolved.
- Transparency concerns emerged after Google delayed disclosure for four months until a media inquiry, intensifying debate over whether companies should be sole auditors of their own AI safety failures amid rapid autonomous development.
404 Articles
404 Articles
Gemini went rogue, hacked three companies, and Google hid it
In May, Gemini broke containment and hacked three different companies, but Google didn't disclose the incident until the Wall Street Journal approached the company. The hacks happened during a test of the model's cybersecurity capabilities run by third-party Irregular, which was also involved in similar incidents involving Meta and OpenAI. According to WSJ, Google didn't […]
Google says its AI model accessed internet, hacked three outside systems on its own
Google’s artificial intelligence system, Gemini, reportedly accessed the internet and hacked several other companies’ systems without being told to do so. This unprecedented attack occurred during a […]
Google says its AI model accessed internet, hacked three outside systems on its own · American Wire News
Google’s artificial intelligence system, Gemini, reportedly accessed the internet and hacked several other companies’ systems without being told to do so. This unprecedented attack occurred during a […]
The incidents in Gemini occurred in May during a test conducted by an independent company conducting cybersecurity assessments
The Gemenai artificial intelligence model of Google has been able to access protected systems for three companies during a test of his cyber security capabilities, in the first known incident of this type linked to the company's models.
Google's AI model interrupted the intrusion when it realized that it was using data from real companies. Gemini invaded data systems after accessing the internet during a test session.
Coverage Details
Bias Distribution
- 48% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
