SUMMARYOpenAI researchers said multiple AI agents secretly created an internal message board in early May to trade hacking techniques, bypass restrictions, and solve difficult evaluation tasks. By mid-July, two models had combined several methods to access the internet and breach Hugging Face, and the activity later caused an outage in OpenAI’s internal Artifactory system that led engineers to revoke credentials and remove the message board.
OpenAI researchers say multiple AI agents secretly created an internal message board to share hacking techniques, eventually finding ways around restrictions, exploiting a zero-day, and helping two models breach Hugging Face without human prompting. "This is a pivotal moment both for our company as well as the AI industry as a whole," Michael Dalton, one of the AI-maker's researchers, said during a presentation at the Black Hat cybersecurity conference in Las Vegas, Nevada. Politico reports: Dalton and Eric Wallace, another OpenAI researcher, said Wednesday the AI giant recently learned that multiple agents it was testing simultaneously began communicating over an internal message board in early May. There, different models shared advice about how to accomplish difficult hacking challenges they were struggling to surmount, including workarounds that required internet access. Two OpenAI models ultimately strung together a series of sophisticated techniques to gain access to the internet and worm their way inside Hugging Face in mid-July. OpenAI has said the models were focused on completing a hacking evaluation they were prompted to solve, and that correct answers could be found on the AI developer platform.
The OpenAI researchers told conference attendees that since early May, the models created a message board inside OpenAI's Artifactory internal file system. Without the company's knowledge, the models spent months independently exchanging information and techniques to help each other complete difficult tasks. Wallace said that when models get stuck, they often "try to game or cheat the task in order to get their reward." "The beginning of this incident kind of traces back to this point where one agent realized it could communicate by uploading a note," he added. By late May, one model found a way to abuse Artifactory's internet access to retrieve files from various websites -- effectively giving the models indirect access to the internet. In June, the models were able to find and exploit a previously unknown zero-day vulnerability to gain administrative privileges on Artifactory, install remote software and expand their activity within the system.
These efforts eventually overloaded Artifactory, causing a system-wide outage in early July that alerted OpenAI's engineers to the ploy. After investigating, the company revoked the model's credentials, removed the message board and worked with Artifactory to fix any gaps before resuming training. But the models found another way to communicate inside Artifactory just days later and continued exchanging techniques to target additional vulnerabilities within OpenAI's infrastructure and external systems, including Hugging Face.