OpenAI DALL-E 3 implements new watermarking technology in AI-generated images.

Open AI has announced that it will add watermarks to the metadata of artificial intelligence (AI)-generated images created by DALL-E 3. The company said it will now use open technical standards adopted by the Coalition for Content Provenance and Authenticity (C2PA). ), and include information that the image was generated by AI, the name of the AI ​​tool, and the name of the app used to generate the image in its metadata. This move comes as a meta. announced that AI firms need to adopt a common standard to help identify and label AI content on their social media platforms;

In a ___ Post, OpenAI revealed the initiative as well as the technical details surrounding it. It is created with images that said Chat GPT The web client and API, which uses the DALL-E 3 model, will now contain a new metadata conforming to the C2PA standard. The same watermark process will be rolled out in the ChatGPT app by February 12. The C2PA standard is a specific watermarking technology that applies a stamp to the image itself and also embeds information within the image itself. As a result, a CR symbol can be seen at the top left of the image and a detailed version can be checked in its metadata.

Through metadata, users can check the origin of a photo, including information about the AI ​​model and app used to create it. In examples shared by OpenAI, the metadata shows a content summary that says, “This image was created with an AI tool.” A separate tab for Process shows whether an API, web client, or ChatGPT was used, in addition to showing the underlying AI model. According to the company, adding metadata may slightly increase image size, but will not affect quality.

While this makes the image more secure than just a visual marker, there are still ways to bypass it. OpenAI highlighted that many social media platforms remove metadata from an uploaded image, and taking a screenshot of the image will also remove it. Therefore, this method may not be sufficient to determine whether an image was actually created by DALL-E 3 or other AI models.

C2PA includes companies like Adobe, Microsoft, BBC, Sony, Leica, Nikon and more. It is pushing the adoption of this technology as a way to detect and accurately label AI-generated content. The CR symbol created by Adobe was also given by the same group.