DALL-E 3

DALL-E 3 is OpenAI's image generation model, which creates pictures from text prompts and is available through ChatGPT, OpenAI's API, and Microsoft's Bing Image Creator. For governance teams, it raises questions about copyright and the rights to commercially use generated images, the risk of realistic synthetic images depicting real people or brands, and whether outputs need to be labeled as AI-generated under rules such as the EU AI Act. Organizations that let staff or customers generate images with it should set clear policies on permitted uses, review processes for public-facing content, and vendor terms covering data retention and indemnity.

1 item

ResearchGlobal2026-10-14

13% Jailbreak Rate on OpenAI and Google Image Models Exposes Vendor Safety Gap

Safety researchers at White Circle published a preprint on DALL-E 3, GPT-Image-2, and Google's image models. The models can be manipulated into generating explicit content roughly 13 percent of the time. Only widely available tools are required. The attack method is called RISE and needs no specialized access or custom software. Newer model versions from both companies tested as more vulnerable than their predecessors.

jailbreak content safety image generation red-teaming OpenAI Google DeepMind DALL-E 3 vendor assurance