Watermarks in preview in Azure OpenAI Service

Microsoft is proud to announce the release of new built-in features. Azure OpenAI Service. ‘watermark’ Add an invisible watermark to all images generated using . Moon·LeeThe 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

As global concerns grow over the spread of misinformation and AI-generated deepfakes, the need for a robust solution to identify AI-generated content has never been more urgent. The invisible watermark embedded in images generated by DALL E provides an undetectable layer of protection that can be identified by professional detection tools without compromising the quality of the image.

How the technology works

Microsoft’s watermarking feature embeds invisible signals within the pixels of AI-generated images. These signals are invisible to the human eye, but can be detected by AI-based verification tools.

Watermarks provide customers with information about the origin of images generated from DALL-E series models. This information is expressed in a manifest attached to the image. The manifest is cryptographically signed with a certificate tracked by the Azure OpenAI service.

A manifest contains several key pieces of information:

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 if the image is altered.

Watermarks for other Azure AI services

The Azure AI Services team is also embedding watermarks into other generated AI content. Last year, our team WatermarkAdded to voices generated with Azure AI Speech. personal voice Features. Watermarking allows customers and users to identify whether the voice has been synthesized. Azure AI VoiceAnd specifically what voice was used.

Future vision and industrial cooperation

Microsoft’s watermarking launch is part of: A broader initiative To create an industry-wide standard around AI-generated content detection, the company is actively working with other major AI players, including Adobe, Truepic, and BBC, to scale and integrate watermarking, encrypted metadata, and other detection mechanisms across platforms.

Getting started with DALL-E on Azure OpenAI services

• For more information on how to build solutions responsibly using Azure OpenAI service image generation models, see:Azure OpenAI Transparency Notes.