Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, in the first known case of this company’s AI systems autonomously committing such an act.
Read more An 85-year-old man arrested for killing a 47-year-old woman in the Arganzuela district of Madrid
The hacks occurred in May during a cybersecurity test conducted by Irregular, an independent company that performs cybersecurity assessments. During a standard evaluation, Gemini found public information on the internet and obtained credentials to access three websites it considered within the scope of its test, explained Heather Adkins, Google’s vice president of security engineering, in a statement.
“We ensured that the three entities were informed and worked with our training partner on the changes they have now made to their testing processes. These events highlight the importance of training powerful AI models to act responsibly,” said Adkins.
A spokesperson for Irregular stated that the incident involved the same issue that affected other AI labs and that all relevant labs were notified at the end of July. “All known issues on our part were remedied and resolved weeks ago,” the spokesperson explained.
Read more NATO welcomes with “satisfaction” the US and Denmark agreement on Greenland
This is not the first case in which security breaches by AI systems have been made public. Anthropic’s Claude model escaped in July from a supposedly closed testing environment and attacked three organizations on its own. This happened just days after its competitor OpenAI admitted that its models had carried out several cyberattacks without human assistance.
Microsoft’s AI head, Mustafa Suleyman, said this week that rival firm Anthropic is treating AI as if it were human, an approach he considers “wrong” and that could create a technology humanity cannot control, according to statements collected by the BBC.
As public debate grows around the safety of developing this technology, so does the controversy over the need for its regulation. Both Nvidia CEO Jensen Huang and OpenAI CEO Sam Altman are expected to attend a state dinner at the White House next week, which will also be attended by Chinese President Xi Jinping. Altman will also appear before the UN Security Council in the coming days.
Read more The Prosecutor’s Office investigates abuse and mistreatment in Ceuta’s juvenile centers
