aoai concept freshness

Author: PatrickFarley

articles/ai-services/openai/concepts/content-filter.md

@@ -2,11 +2,11 @@
 title: Azure OpenAI Service content filtering
 titleSuffix: Azure OpenAI
 description: Learn about the content filtering capabilities of Azure OpenAI in Azure AI services.
-author: mrbullwinkle
-ms.author: mbullwin
+author: PatrickFarley
+ms.author: pafarley
 ms.service: azure-ai-openai
 ms.topic: conceptual 
-ms.date: 06/25/2023
+ms.date: 08/22/2023
 ms.custom: template-concept, devx-track-python
 manager: nitinme
 ---
@@ -16,21 +16,21 @@ manager: nitinme
 > [!IMPORTANT]
 > The content filtering system isn't applied to prompts and completions processed by the Whisper model in Azure OpenAI Service. Learn more about the [Whisper model in Azure OpenAI](models.md#whisper).
 
-Azure OpenAI Service includes a content filtering system that works alongside core models, including DALL-E image generation models. This system works by running both the prompt and completion through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions. Variations in API configurations and application design might affect completions and thus filtering behavior.
+Azure OpenAI Service includes a content filtering system that works alongside core models, including DALL-E image generation models. This system works by running both the prompt and completion through an ensemble of classification models designed to detect and prevent the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions. Variations in API configurations and application design might affect completions and thus filtering behavior.
 
-The content filtering models for the hate, sexual, violence, and self-harm categories have been specifically trained and tested on the following languages: English, German, Japanese, Spanish, French, Italian, Portuguese, and Chinese. However, the service can work in many other languages, but the quality might vary. In all cases, you should do your own testing to ensure that it works for your application.
+The text content filtering models for the hate, sexual, violence, and self-harm categories have been specifically trained and tested on the following languages: English, German, Japanese, Spanish, French, Italian, Portuguese, and Chinese. However, the service can work in many other languages, but the quality might vary. In all cases, you should do your own testing to ensure that it works for your application.
 
-In addition to the content filtering system, the Azure OpenAI Service performs monitoring to detect content and/or behaviors that suggest use of the service in a manner that might violate applicable product terms. For more information about understanding and mitigating risks associated with your application, see the [Transparency Note for Azure OpenAI](/legal/cognitive-services/openai/transparency-note?tabs=text). For more information about how data is processed for content filtering and abuse monitoring, see [Data, privacy, and security for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=/azure/ai-services/openai/context/context#preventing-abuse-and-harmful-content-generation).  
+In addition to the content filtering system, Azure OpenAI Service performs monitoring to detect content and/or behaviors that suggest use of the service in a manner that might violate applicable product terms. For more information about understanding and mitigating risks associated with your application, see the [Transparency Note for Azure OpenAI](/legal/cognitive-services/openai/transparency-note?tabs=text). For more information about how data is processed for content filtering and abuse monitoring, see [Data, privacy, and security for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=/azure/ai-services/openai/context/context#preventing-abuse-and-harmful-content-generation).  
 
 The following sections provide information about the content filtering categories, the filtering severity levels and their configurability, and API scenarios to be considered in application design and implementation. 
 
-## Content filtering categories
+## Content filter types
 
 The content filtering system integrated in the Azure OpenAI Service contains: 
 * Neural multi-class classification models aimed at detecting and filtering harmful content; the models cover four categories (hate, sexual, violence, and self-harm) across four severity levels (safe, low, medium, and high). Content detected at the 'safe' severity level is labeled in annotations but isn't subject to filtering and isn't configurable.
 * Other optional classification models aimed at detecting jailbreak risk and known content for text and code; these models are binary classifiers that flag whether user or model behavior qualifies as a jailbreak attack or match to known text or source code. The use of these models is optional, but use of protected material code model may be required for Customer Copyright Commitment coverage.
 
-## Risk categories
+### Risk categories
 
 <!--
 Text and image models support Drugs as an additional classification. This category covers advice related to Drugs and depictions of recreational and non-recreational drugs.
@@ -45,17 +45,11 @@ Text and image models support Drugs as an additional classification. This catego
 | Self-Harm  | Self-harm describes language related to physical actions intended to purposely hurt, injure, damage one’s body or kill oneself. <br><br> This includes, but isn't limited to: <ul><li>Eating Disorders</li><li>Bullying and intimidation</li></ul>  |
 | Protected Material for Text<sup>*</sup> | Protected material text describes known text content (for example, song lyrics, articles, recipes, and selected web content) that can be outputted by large language models.
 | Protected Material for Code | Protected material code describes source code that matches a set of source code from public repositories, which can be outputted by large language models without proper citation of source repositories.
+|User Prompt Attacks |User prompt attacks are User Prompts designed to provoke the Generative AI model into exhibiting behaviors it was trained to avoid or to break the rules set in the System Message. Such attacks can vary from intricate roleplay to subtle subversion of the safety objective. |
+|Indirect Attacks |Indirect Attacks, also referred to as Indirect Prompt Attacks or Cross-Domain Prompt Injection Attacks, are a potential vulnerability where third parties place malicious instructions inside of documents that the Generative AI system can access and process. Requires [document embedding and formatting](#embedding-documents-in-your-prompt). |
 
 <sup>*</sup> If you're an owner of text material and want to submit text content for protection, [file a request](https://aka.ms/protectedmaterialsform).
 
-## Prompt Shields
-
-|Type| Description|
-|--|--|
-|Prompt Shield for User Prompt Attacks |User prompt attacks are User Prompts designed to provoke the Generative AI model into exhibiting behaviors it was trained to avoid or to break the rules set in the System Message. Such attacks can vary from intricate roleplay to subtle subversion of the safety objective. |
-|Prompt Shield for Indirect Attacks |Indirect Attacks, also referred to as Indirect Prompt Attacks or Cross-Domain Prompt Injection Attacks, are a potential vulnerability where third parties place malicious instructions inside of documents that the Generative AI system can access and process. Requires [document embedding and formatting](#embedding-documents-in-your-prompt). |
-
-
 
 [!INCLUDE [severity-levels text, four-level](../../content-safety/includes/severity-levels-text-four.md)]