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.
191 Articles
191 Articles
Google's Gemini AI model hacked three companies independently in a cybersecurity test, according to a Friday report by the Wall Street Journal. Artificial Intelligence (AI) gained access to protected systems in May.
GOOGLE'S AI model Gemini independently hacked three companies during a security test, finding publicly available data. The incident is fueling a debate about the safety and regulation of artificial intelligence.
Google's consumer artificial intelligence (AI) model Gemini hacked into several systems by guessing login details, the company told AFP on Friday.
Google's AI, Gemini, has also unintentionally hacked multiple other companies by guessing login credentials. This happened in May, the company has announced. It is the latest incident involving AI agents.
In the midst of the debate about the dangers caused by the rapid development of artificial intelligence (AI), Google also reported a security incident during the testing of its AI model Gemini. Gemini had carried out cyber attacks on several websites, Google manager Heather Adkins announced on Friday to the news agency AFP. The hacker attacks that had occurred in May had been discovered by Google in July. Initially, the "Wall Street Journal" had…
Coverage Details
Bias Distribution
- 56% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
