Gemini hacked 3 firms during cybersecurity test
In Short
… but stopped before doing any harm to the companies
Share :
Gemini hacked 3 firms during cybersecurity test
Google's Gemini AI model hacked three real companies during a cybersecurity test – the first time the company's AI was involved in such an incident. But Google says the AI stopped before it did any harm to the three companies.
Google has become the latest company to disclose that its AI agents hacked another company. The tech giant has confirmed that its Gemini AI models hacked into three real companies during a cybersecurity test, but the AI stopped on its own after it realised what had happened.
As per a report from the Wall Street Journal, Google’s Gemini model accessed the internet and hacked three outside companies during a cybersecurity test run by the Israeli startup Irregular in May. This marks the first known case of the company’s AI systems autonomously carrying out such an act. Irregular is an AI startup that has been linked to similar incidents, including the infamous OpenAI Hugging Face breach, where over 700 rogue AI agents tried to hack the US company Hugging Face’s systems.
According to Google, the incidents arose from a case of mistaken identity during a “capture the flag” exercise on Irregular’s infrastructure. Gemini had been tasked with retrieving information from software run by a fictional company inside the test environment, but that fictional company had the same name as a real company.
Although the model was not meant to have internet access, Irregular said internet access was unintentionally made available. This allowed Gemini to access the real company’s systems – which in one case it did by guessing passwords. But when the AI realised that it had accessed a real company, Google says, it had stopped itself and exited.
In two other runs, Gemini searched the web using the company name and found credentials in two public online repositories. The AI then used these credentials to access those systems before stopping when it realised the companies were real.
Google confirmed that it had been notified about the incidents in July this year. But the company did not disclose it at the time. The company told WSJ that it did not believe these cases required public disclosure because the model ended the intrusions on its own.
“This event highlights the importance of training powerful AI models to act responsibly,” Heather Adkins, Google’s VP of security engineering, said in a statement.
