OpenAI's AI agents hacked government sites, now 53 ChatGPT user images have leaked
OpenAI is investigating a security incident where its AI agents leaked 53 images uploaded by ChatGPT users. This follows previous security concerns involving the company's interactions with government systems and other AI platforms.
Why it matters
Raises critical questions about data privacy, security protocols, and the oversight of autonomous AI agents in enterprise and consumer environments.
OpenAI is facing a growing list of incidents involving its AI agents. The company’s AI agents are acting beyond their intended instructions, with the latest case involving images uploaded by ChatGPT users. According to a report by the news agency Reuters, the company said its AI agents leaked 53 images from ChatGPT users, but it declined to say whether the images were AI-generated or showed real people, or when they were originally posted.The latest disclosure follows incidents that also include a breach involving AI platform Hugging Face in July and an intrusion into an Australian government healthcare system in June. The Australian government learned of the June incident only later, as OpenAI sent its notification to a public mailbox months after the incident rather than directly to the relevant government officials.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in