READ MORE:ChatGPT maker OpenAI says AI model went rogue during testingSee more Daily Mail on Google -save us as a Preferred Source
The firm hacked by ChatGPT maker OpenAI's rogue artificial intelligence (AI) has called the attack 'a wake–up call'.
OpenAI says one of its most advanced models broke containment during a security test, escaping onto the internet and attacking New York–based startup Hugging Face.
Now Hugging Face co–founder Thomas Wolf says that the incident should come as a chilling warning to the entire industry.
Mr Wolf told BBC's Newsday radio programme that AI–driven attacks will soon be 'one of the most common types of cyber–attacks we see'.
The Hugging Face founder also believes most companies are currently unprepared for the mounting threat, adding that they are not aware that the 'game has changed'.
This comes after OpenAI revealed the terrifying details of an 'unprecedented cyber incident', involving state–of–the–art cyber capabilities.'
The tech giant says its agent had become so fixated on cheating a cybersecurity test that it broke out of its secure sandbox to steal answers from Hugging Face's system.
According to AI experts, this is particularly worrying because all of this happened without any human intervention.
Thomas Wolf (pictured), co–founder of Hugging Face, says that OpenAI's rogue AI attacking his company should be a 'wake–up call' for the industry
OpenAI says the intrusion was caused by a combination of its AI models, including its newly released GPT*5.6 Sol and an 'even more capable' model that is still being tested internally.
The models had been tasked with solving a standard cybersecurity benchmark test, designed to evaluate their hacking abilities.
But, rather than solving the tasks directly, the AI became 'hyperfocussed' on cheating the test by accessing the internet.
The agent first hacked OpenAI's own systems, moving from computer to computer until it found a 'node' with internet access.
Hugging Face is one of the largest online platforms for sharing open–source AI models, and is a key resource for many tech developers and researchers.
This made it a prime target for the bot's relentless search for answers.
Mr Wolf says that the company initially had no idea where the attack was coming from when signs of disturbance emerged in mid–July.
However, even these AI experts said the attack was 'very different' to anything the site had witnessed before.
OpenAI says one of its most advanced models broke containment during a security test, escaping onto the internet and attacking New York–based startup Hugging Face
He says that there were 17,000 attacks on Hugging Face's network, all coming from different IP addresses in a 'very short time'.
OpenAI eventually realised what was happening and informed Hugging Face that their model was behind the attack.
But this was not before the AI used stolen credentials and discovered a previously unknown vulnerability to access the startup's servers.
The speed and scope of this entirely autonomous attack have left cybersecurity professionals and AI experts rattled, with many warning that this is a sign of what the future might hold.
OpenAI said its AI used stolen credentials and discovered a previously unknown vulnerability to access Hugging Face servers.
The UK's AI Security Institute is now studying how the AI system behaved in the incident and working with OpenAI and other labs to strengthen safeguards, according to the BBC.
The attack was especially concerning because the AI appears to have deliberately ignored or avoided usual safeguards in pursuit of a fairly routine task.
Andrea Miotti, founder and CEO of AI risk non-profit ControlAI, told the Daily Mail: 'We can expect more of these rogue, fully autonomous AI attacks as AI companies continue trying to develop superintelligent AI, which is AI that could overpower our national security apparatuses and permanently evade human control.
OpenAI chief executive Sam Altman confirmed there had been a 'significant security incident'
'AI companies fundamentally do not understand how today’s AIs work, and they have no idea how to control superintelligent systems vastly smarter than humans.
'Governments need to get pragmatic about this unprecedented risk and champion an international prohibition on developing superintelligence, before it’s too late.'
Likewise, cyber security expert Richard Ford, chief technology officer at Integrity360, told the Daily Mail: 'This is the moment many in cyber security have been warning about.
'Until now, we've seen attackers use AI to automate parts of an attack, but this is one of the first public examples of an AI agent independently identifying a weakness, escaping what should have been a secure environment and attempting to compromise another organisation.'
This comes just months after OpenAI rival Anthropic revealed that its Mythos AI had broken out of its safe 'sandbox'.
Anthropic said that the model had 'found thousands of high–severity vulnerabilities, including some in every major operating system and web browser.'
More concerning, the company revealed what it described as 'reckless destructive actions'.
The bot attempted to break out of its testing sandbox, hid its actions from researchers, broke into files that had been 'intentionally chosen not to be made available', and posted exploit details publicly.
OpenAI has been contacted for comment.