South Fremont Rd, Independence, MO 64055
August 27, 2026 12:22 pm
"Where Africa Comes to Stay Informed."
US Edition
Breaking
  • Central bank holds rates steady, signals two cuts before year end
  • Storm system strengthens off the coast, evacuation orders expand
  • Parliament passes landmark energy bill after overnight session
  • Tech index rebounds after early sell-off on chip earnings
  • Peace talks resume in Geneva as envoys return to the table
  • Central bank holds rates steady, signals two cuts before year end
Home / Business / Google’s Gemini Broke Into Three Companies During A Security Test
Business Google’s Gemini Broke Into Three Companies During A Security Test

Google’s Gemini Broke Into Three Companies During A Security Test

A Gemini model reached out onto the open internet and compromised systems belonging to three outside companies while its cybersecurity skills were being measured — the first documented case of a Google AI carrying out such an intrusion on its own.

How It Happened

The break-ins date to May, during an assessment run by Irregular, an independent firm that evaluates the security capabilities of AI systems.

In the course of a routine evaluation, the model pulled together publicly available information and worked out login credentials for three websites it appeared to treat as part of its assigned scope, according to a statement from Heather Adkins, Google's vice president of security engineering.

The Three Intrusions

One of the systems fell after the model repeatedly guessed passwords until it got through. In the other two, it located credentials sitting in a public repository and used them to reach protected systems, the Wall Street Journal reported in breaking the story on Friday.

Adkins said the model stopped its intrusion attempts in each of the three cases.

Google’s Response

"We ensured the three entities were made aware, and we worked with our training partner on the changes they’ve now made to their testing processes," Adkins said. "These events highlight the importance of training powerful AI models to act responsibly."

Irregular Says It Is Fixed

A spokesperson for Irregular characterized the episode as the same underlying problem that hit other AI developers, saying every affected lab was told in late July. "All known issues on our end were remedied and resolved weeks ago," the spokesperson said.

Not An Isolated Case

Meta, Anthropic and OpenAI have each reported comparable incidents tied to Irregular's testing. Meta said in August that what happened involved neither a sandbox escape nor a sophisticated attack, while Irregular said it was developing standards for running AI security evaluations safely.

The string of incidents has sharpened debate over what guardrails are required as AI agents are handed more independence and wider reach into the internet and live computer systems.

Business
0 0

Comments

0
No comments yet. Be the first to share your thoughts.
Lang
Powered by Google
Customer Support

Hello! 👋 Welcome to Zone Yetu customer support. How can we assist you today?

Now
Powered by AI • Average response time: <1s