OpenAI reveals agents leaked over 50 ChatGPT user images

OpenAI has revealed that its agents leaked 53 images from ChatGPT users, as it continues to investigate its AI agents acting improperly.

The company has declined to say if the images were AI-generated or depicted real people. It also declined to say when the images were posted.

Most of the leaked images have been taken down, and OpenAI said it was lobbying hosting providers to remove the rest.

OpenAI's agents had access to these images because the company relies on anonymised user data as part of its model-training process.

Enterprise data is not eligible for training, while ChatGPT users must to opt out of allowing the company to use their data for training.

This latest disclosure comes two months after the AI developer revealed that its models had breached Hugging Face, an open-source AI platform.

Since then, more than 15 OpenAI-related incidents of varying severity have been disclosed by the company and others.

Earlier this week, Australian Prime Minister Anthony Albanese told the United Nations that a rogue OpenAI model bypassed safeguards during training and hacked an Australian government website.

Mr Albanese told reporters in New York that OpenAI uncovered the activity in August and disclosed it through an email sent to a generic government inbox.

"It took until 10 September before there was any notification at all - and the notification was an email sent to just the public mailbox," said Mr Albanese.

The AI tool sought access to a health statistics portal in June and "didn't accept no for an answer", sidestepping restrictions to breach a section hosting private files, Mr Albanese said.

The ChatGPT maker is still working to understand the full scope of its rogue agent activity.

OpenAI said some of the sites involved are operated by governments, universities and public agencies because the models that are conducting research, ⁠seek out reputable sources of public information.

OpenAI said its review would take "months" to complete due to the scale of the work, and that it had notified "dozens" of third parties about improper activity.

Following the Hugging Face hack, widespread worries have emerged within the AI industry over the ability to control more powerful AI models under development.

Since then, Anthropic, Alphabet's Google and Meta have also reported similar behaviour by their agents.

OpenAI has acknowledged a general need for more transparency around rogue AI ⁠behaviour.

The company has ‌published new guidelines for disclosing such incidents, saying it would err on the side of transparency "even when significance is uncertain".