GA release of Protected Material Detection in Azure AI Content Safety and Azure OpenAI Service

  • Thread starter Thread starter Sherry_Shao
  • Start date Start date
S

Sherry_Shao

We are thrilled to announce the GA release of Protected Material Detection in Azure AI Content Safety and Azure OpenAI Service. We previously announced the preview of Protected Material Detection in November 2023.

Protected Material Detection is a feature designed to guard against outputs that could potentially violate copyright. Many customers and end users are apprehensive about the risk of IP infringement claims when integrating and using Generative AI. To address these concerns, we have introduced this new feature that specifically targets LLM model completions and scans for matches against an index of third-party text content to detect the usage of third-party text content, including songs, news articles, recipes, and selected web content.

Protected Material Detection APIs



Jinrui_Shao_3-1725375306002.png





Users have the flexibility to specify the content they wish to check in their API requests. Upon receiving these specifications, the API processes the request and returns a response. This response includes a Boolean value that clearly indicates the detection results. If the Boolean is 'true,' it signifies that the submitted content has been identified as Copyright Violation. Conversely, a 'false' value implies that no such matches were found.

Protected Material Detection in Azure OpenAI

Jinrui_Shao_1-1725375261267.png



User Scenarios

The key objectives of the "Protected Material Detection for Text" feature for GenAI-generated content are:

  • To detect and prevent the display of protected content generated by AI models.
  • To enable organizations to manage risks associated with AI-generated content.
  • To ensure that AI-generated content complies with legal, ethical, and content policy guidelines.



  1. Content Generation Platforms for Creative Writing
  • Scenario: A content generation platform that uses GenAI for creative writing (e.g., blog posts, stories, songs, marketing copy) integrates the "Protected Material for Text" feature to prevent the generation of content that closely matches known copyrighted material.
  • User: Platform administrators and content creators.
  • Action: The platform uses Azure AI Content Safety to scan AI-generated content before it is provided to users. If the generated text matches protected material, the content is flagged and either blocked or revised.
  • Outcome: The platform avoids potential copyright infringements and helps support that generated content is original and compliant with intellectual property laws.



Jinrui_Shao_2-1725375261282.png





  1. Automated Social Media Content Creation
  • Scenario: A digital marketing agency uses GenAI to automate social media content creation. The agency integrates the "Protected Material for Text" feature to avoid publishing AI-generated content that includes copyrighted text, such as song lyrics or excerpts from books.
  • User: Digital marketers and social media managers.
  • Action: The agency employs Azure AI Content Safety to check all AI-generated social media content for matches against a database of protected material. Content that matches is flagged for revision or blocked from posting.
  • Outcome: The agency uses the feature to support compliance with copyright laws and avoids reputational risks associated with posting unauthorized content.
  1. AI-Assisted News Writing
  • Scenario: A news outlet uses GenAI to assist journalists in drafting articles and reports. To ensure the content does not unintentionally replicate protected content in news articles or other copyrighted material, the outlet uses the "Protected Material for Text" feature.
  • User: Journalists, editors, and compliance officers.
  • Action: The news outlet integrates Azure AI Content Safety into its content creation workflow. AI-generated drafts are automatically scanned for protected content before submission for editorial review.
  • Outcome: The news outlet prevents accidental copyright violations and maintains the integrity and originality of its reportin
  1. AI-Powered Recipe Generators
  • Scenario: A food and recipe website uses GenAI to generate new recipes based on user preferences. To avoid generating content that matches protected recipes from famous cookbooks or websites, the website integrates the "Protected Material for Text" feature.
  • User: Content managers and platform administrators.
  • Action: The website uses Azure AI Content Safety to check AI-generated recipes against a database of known protected content. If a generated recipe matches a protected one, it is flagged and revised or blocked.
  • Outcome: The website ensures that all AI-generated recipes are original, reducing the risk of copyright infringement.



Reference Links


Continue reading...
 
Back
Top