Watermarks in preview in Azure OpenAI Service
Microsoft is proud to announce the rollout of a new built-in feature in Azure OpenAI Service. ‘Watermarks’ add invisible watermarks to all images generated using DALL·E, the company’s flagship generative AI image generator. This watermarking technology is designed to provide an additional layer of transparency and protection to AI-generated content.
The Importance of Watermarking AI-Generated Content
With global concerns rising over the spread of disinformation and AI-generated deepfakes, the need for robust solutions to identify AI-created content has never been more urgent. The invisible watermark embedded in DALL·E-generated images provides an undetectable layer of protection that can be identified by specialized detection tools without affecting the image’s quality.
How the Technology Works
Microsoft’s watermarking feature embeds invisible signals within the pixels of AI-generated images. These signals are imperceptible to the human eye but detectable by AI-based verification tools.
Watermarks provide customers with information about the origin of an image generated by the DALL-E series models. This information is represented by a manifest attached to the image. The manifest is cryptographically signed by a certificate that traces back to Azure OpenAI Service.
The manifest contains several key pieces of information:
Field name
Field content
“description”
This field has a value of ”AI Generated Image” for all DALL-E model generated images, attesting to the AI-generated nature of the image.
“softwareAgent”
This field has a value of ”Azure OpenAI DALL-E” for all images generated by DALL-E series models in Azure OpenAI Service.
“when”
The timestamp of when the Content Credentials were created.
The watermarking process is robust and resilient to common modifications such as resizing or cropping, ensuring that the integrity of the watermark remains intact even when images are altered.
Watermarks in other Azure AI services
The Azure AI services team is also embedding watermarks into other generative AI content. Last year, our team announced that watermarks are added to voices created with the Azure AI Speech personal voice feature. Watermarks allow customers and users to identify whether speech is synthesized using Azure AI Speech, and specifically, which voice was used.
Future Vision and Industry Collaboration
Microsoft’s watermarking launch is part of a broader initiative to create industry-wide standards around the detection of AI-generated content. The company is actively collaborating with other major AI players, including Adobe, Truepic and the BBC to ensure that watermarking, cryptographic metadata, and other detection mechanisms can be scaled and integrated across platforms.
Get started with DALL-E in Azure OpenAI Service
Use DALL·E in Azure OpenAI Service Studio
Use DALL·E in Azure AI Studio
Learn more about watermarks
For more information on how to responsibly build solutions with Azure OpenAI Service image-generation models, visit the Azure OpenAI transparency note.
Microsoft Tech Community – Latest Blogs –Read More