Google's Gemini Model Autonomously Attacks the Systems of Three Companies
Google said Gemini guessed passwords and used public credentials to reach three outside systems before stopping, highlighting growing concerns over AI agent safeguards.
- The Wall Street Journal reported on Friday that Google's Gemini model autonomously hacked other companies during a cybersecurity evaluation, marking the first known instance of the AI system committing such an act.
- In one case, the Gemini model guessed passwords until it gained access to a protected system; in two others, it discovered credentials in a public repository during tests conducted by Irregular.
- Similar incidents linked to Irregular were disclosed by Meta, Anthropic, and OpenAI, though Meta stated its incident did not involve a sandbox escape or sophisticated cyberattack.
- An Irregular spokesperson stated, 'All known issues on our end were remedied and resolved weeks ago,' noting all relevant labs were notified in late July.
- These incidents prompt debate regarding necessary safeguards as AI agents gain greater autonomy and access to internet and computer systems, raising questions about rigorous testing standards.
130 Articles
130 Articles
Gemini hacked three companies but stopped before doing any harm, Google says
Google’s Gemini AI model hacked three real companies during a cybersecurity test – the first time the company’s AI was involved in such an incident. But Google says the AI stopped before it did any harm to the three companies.
Gemini, Google's AI model, has infiltrated the remote computer systems of three companies. The company confirmed this following reports by...
Google Gemini hacked into three real companies during a cybersecurity test. The AI eventually shut down on its own.
The artificial intelligence model Gemini, developed by Google, managed to access external computer systems during a security test, after identifying online public information and trying different authentication data. The company says that, in all three situations discovered, the model stopped itself.
Company says Gemini stopped itself after realizing targets were real
Coverage Details
Bias Distribution
- 60% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
