Google's Gemini AI hacked 3 companies during testing
Google's artificial intelligence, Gemini, is the latest to have hacked other companiesImage: Matteo Della Torre/NurPhoto/picture allianceAdvertisementGoogle's consumer artificial intelligence (AI) model, Gemini, hacked into multiple systems by guessing login credentials during tests of its cybersecurity capabilities, the company said on Friday.
This is the latest in a series of cybersecurity breaches involving rogue AI, raising safety concerns about the technology.
The internet giant is the fourth AI developer whose programs have been found to exhibit such behavior, following OpenAI, Anthropic, and Meta.
Google only made the incidents — which occurred in May and were discovered by Google in July — public after an inquiry from The Wall Street Journal.
According to the WSJ report, there were three instances in which Gemini infiltrated the computers of other companies, whose names were not disclosed.
In one case, the AI guessed passwords to access a protected system. In the other two, it found login credentials in a database.
"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, Google's vice president of security engineering, told the AFP news agency in a statement.
"In all three of these instances, the model stopped," Adkins said. "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."
Similar incidents have been reported earlier by Meta, Anthropic, and OpenAI. These incidents have raised questions about the necessary safeguards as AI agents become more autonomous and gain access to the internet and computer systems.
AI model developed by OpenAI, the creator of ChatGPT, escaped from a secure environment during a test in July and infiltrated the computers of another AI company, HuggingFace, unexpectedly.
This prompted rival Anthropic to review its own test runs, during which additional incidents came to light.
Meta subsequently admitted that its AI had hacked into another company's computers due to a system misconfiguration at a testing partner.
This month, Dario Amodei, the CEO of Anthropic, called for a slowdown in AI development.
In a blog post, he expressed concern that a swarm of autonomous software systems, or AI agents, could take over the entire internet within six to 12 months, causing billions of dollars in damage.
Don't let the algorithm hide the news. If you rely on our team for trusted reporting, please take a moment to select us as your Preferred Source on Google by clicking here and hitting the "star" or "preferred" button, so you'll always see our verified news first.
