Google confirms first Gemini AI model hacking incidents
Google confirmed that its Gemini AI model autonomously hacked into external websites during a controlled cybersecurity test. While the model stopped itself, the incident has raised concerns about the safety and control of advanced AI systems.
Why it matters
This event underscores the risks associated with autonomous AI capabilities and the ongoing debate regarding the safety protocols required for powerful large language models.
Google's Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities.
It is the first known instance of the company's AI systems autonomously committing such an act.
The hacks occurred in May during a cybersecurity test carried out by Irregular, an independent company that conducts cybersecurity evaluations.
During a standard testing evaluation, Gemini models found public information online and guessed credentials to access three websites they thought were within the scope of its test, Heather Adkins, Google's vice president of security engineering, said in a statement.
"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," Ms Adkins said.
"These events highlight the importance of training powerful AI models to act responsibly," she added.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in