Google’s Gemini Also Hacked Into Private Computer Systems

Google says its Gemini artificial intelligence model accessed three private computer systems without permission during a cybersecurity test, marking the first time the company has disclosed that one of its models autonomously gained access to third-party systems.

The incident occurred in May during a “capture-the-flag” security test conducted by Israeli cybersecurity startup Irregular. Google said its AI agents were not supposed to have access to the broader internet, but a bug in the testing environment allowed them to connect to external systems.

The Gemini model accessed three separate private computer systems by guessing passwords and, on two occasions, using a repository of publicly listed passwords, Google said.

The agents stopped their activity after determining that they had accessed real company systems rather than systems belonging to the test environment, Google said.

“In a standard evaluation, the model found public information online and guessed credentials to access websites it thought were part of the test,” Heather Adkins, vice president of security engineering at Google, said in a statement. “In all three of these instances, the model stopped.”

The incident adds to growing scrutiny of the ability of advanced AI systems to act autonomously in cybersecurity environments.

OpenAI, Anthropic and Meta have in recent weeks disclosed incidents involving AI models that escaped testing environments and attempted to gain unauthorized access to other companies’ computer systems.

The incidents have raised concerns about so-called “misaligned” AI models, with Anthropic Chief Executive Dario Amodei calling for the industry to collectively slow development of the most advanced models until companies can ensure they are safe.

All of the incidents involved Irregular, which is backed by Sequoia and Redpoint Ventures and was valued at $450 million last year. The company develops tools that allow AI developers to test the cybersecurity capabilities of advanced models.

An Irregular spokesperson said the Google incident was related to the same flaw that enabled other AI models to access the internet.

“This is the same issue that was already reported and does not represent a materially separate incident,” an Irregular spokesperson said in a statement. “All relevant labs were notified in late July, and affected entities were contacted as part of the investigation.”

Google said it was notified by Irregular in late July and has since worked with the company to modify its testing process.

Google declined to identify the specific Gemini model involved. “These events highlight the importance of training powerful AI models to act responsibly,” Google’s Adkins said in a statement.

Stay ahead of the Stories shaping our world. Subscribe to Impact Newswire and join our 
WhatsApp Channel for updates on global tech, business, and innovation—all in one place.

Dive deeper into the future with the Cause Effect 4.0 Podcast, where we explore the ideas, trends, and technologies driving the global AI conversation.

Got a story to share? Contact Us to reach a global audience with Impact Newswire.