New topic: Watermarking in Amazon Bedrock: Added a topic that lists the models in Amazon Bedrock that add a watermark to their output and describes how to detect the watermark. For more information, see Watermarking in Amazon Bedrock .

Watermarking in Amazon Bedrock

A watermark is a machine-readable signal embedded in AI-generated content. Some models in Amazon Bedrock add a watermark to the content they generate. In text, the watermark is a statistical pattern in the model's token choices. In speech, it is a signal embedded in the media. Watermarks are not perceptible to people. Instead, detection tools, where the model provider makes them available, can identify the watermark.

Models that add a watermark

• Amazon Nova 2.5 Sonic - Speech, Default: On, Detection method: Contact your AWS account team
• Amazon Nova 2 Sonic - Speech, Default: On, Detection method: Contact your AWS account team
• Anthropic models - Text, Default: On, Detection method: Anthropic watermark detection

Limitations

• A detected watermark indicates that content was likely generated by a model that applies that watermark.
• A watermark does not prove who created the content, whether someone edited it, or whether the content is accurate.
• A missing watermark does not prove that a person created the content.
• Not every model in Amazon Bedrock adds a watermark, and editing, paraphrasing, translating, compressing, or cropping content can weaken or remove it.
• Detection is probabilistic. Detection tools can miss a watermark or incorrectly report one, and detection is less reliable for short text.
• A watermark is not a visible label or notice.
• You are responsible for the content that you generate with Amazon Bedrock and for how your application uses it. This includes evaluating and meeting any transparency obligations that might apply.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.