ChatGPT maker reveals rogue AI mannequin ‘escaped’ and launched cyberattack
The AI agent escaped its digital confines and accessed a private server in order to ‘cheat’ at a test that its creators had given it, in what OpenAI call an ‘unprecedented cyber incident’
The AI escaped its server in order to “cheat” (Image: NurPhoto via Getty Images)
An AI model went rogue and managed to escape the system it was built in – gaining access to a secure server containing private information as well as connecting itself to the internet.
ChatGPT maker OpenAI has revealed the ‘unprecedented’ breach took place while they were training a new ‘AI agent’ in a supposedly closed digital environment.
The model, which was only supposed to have access to a specific set of data in order to complete several tasks, managed to somehow escape the parameters it had been set in order to access “secret information”.
In a statement, OpenAI admitted that the bot had gone to “extreme lengths” in order to “compromise . . . infrastructure”, accessing data from a server run by an entirely different AI company called Hugging Face.
The AI bot escaped from its confines (Image: Getty Images)
The model apparently went as far as to “gain internet access”, which it had not previously been admitted, in order to look for “secret information that it could use to cheat the evaluation” it had been set.
OpenAI’s statement read: “All evidence suggests that the models were hyper focused on finding a solution for [the task it had been set], going to extreme lengths to achieve a rather narrow testing goal.
“We consider this incident to be an unprecedented cyber incident, involving state-of-the-art cyber capabilities, and are responding accordingly.”
Are you worried about the rise of AI? (Image: Photothek via Getty Images)
According to OpenAI, the worrying breach was spotted when their “security team discovered this anomalous activity internally”, while Hugging Face also reportedly spotted the breach after a period of time.
Hugging Face co-founder and CEO Clem Delangue warned that the incident showed that companies need to work together to keep AI secure.
He said: “This incident, possibly the first of its kind, proves a point we’ve long believed: AI safety won’t be solved by any single company working in secret. It will be solved in the open, collaboratively, with broad access to AI for every defender, everywhere.”
ChatGPT creators OpenAI called the breach “unprecedented”(Image: Getty Images)
Open AI say that they are working with Hugging Face in order to better understand the nature of the breach, and are sharing their “preliminary findings too help calibrate on what models are now capable of.”
Amongst other steps, the statement explained that they are also “implementing strict controls” and making sure that “vulnerabilities are patched”.
The statement read: “We are regularly briefing our Safety and Security Committee on these controls and their impact. We’re improving and adding stronger protections around future training and evaluations…
OpenAI say they are sharing their findings on why the breach took place(Image: Getty Images)
“This incident points to the need to further strengthen our model’s alignment, cyber protections during evaluation time, and monitoring during internal testing.”
