replace term

Author: PatrickFarley

articles/ai-foundry/concepts/ai-red-teaming-agent.md

@@ -17,11 +17,11 @@ author: lgayhardt
 
 The AI Red Teaming Agent (preview) is a powerful tool designed to help organizations proactively find safety risks associated with generative AI systems during design and development of generative AI models and applications.
 
-Traditional red teaming involves exploiting the cyber kill chain and describes the process by which a system is tested for security vulnerabilities. However, with the rise of generative AI, the term AI red teaming has been coined to describe probing for novel risks (both content safety and security related) that these systems present and refers to simulating the behavior of an adversarial user who is trying to cause your AI system to misbehave in a particular way.
+Traditional red teaming involves exploiting the cyber kill chain and describes the process by which a system is tested for security vulnerabilities. However, with the rise of generative AI, the term AI red teaming has been coined to describe probing for novel risks (both content and security related) that these systems present and refers to simulating the behavior of an adversarial user who is trying to cause your AI system to misbehave in a particular way.
 
 The AI Red Teaming Agent leverages Microsoft's open-source framework for Python Risk Identification Tool's ([PyRIT](https://github.com/Azure/PyRIT)) AI red teaming capabilities along with Azure AI Foundry's [Risk and Safety Evaluations](./evaluation-metrics-built-in.md#risk-and-safety-evaluators) to help you automatically assess safety issues in three ways:
 
-- **Automated scans for content safety risks:** Firstly, you can automatically scan your model and application endpoints for safety risks by simulating adversarial probing.
+- **Automated scans for content risks:** Firstly, you can automatically scan your model and application endpoints for safety risks by simulating adversarial probing.
 - **Evaluate probing success:** Next, you can evaluate and score each attack-response pair to generate insightful metrics such as Attack Success Rate (ASR).
 - **Reporting and logging** Finally, you can generate a score card of the attack probing techniques and risk categories to help you decide if the system is ready for deployment. Findings can be logged, monitored, and tracked over time directly in Azure AI Foundry, ensuring compliance and continuous risk mitigation.
 

articles/ai-foundry/concepts/content-filtering.md

@@ -26,7 +26,7 @@ author: PatrickFarley
 
 The content filtering system is powered by [Azure AI Content Safety](../../ai-services/content-safety/overview.md), and it works by running both the prompt input and completion output through a set of classification models designed to detect and prevent the output of harmful content. Variations in API configurations and application design might affect completions and thus filtering behavior.
 
-With Azure OpenAI model deployments, you can use the default content filter or create your own content filter (described later on). Models available through **serverless APIs** have content filtering enabled by default. To learn more about the default content filter enabled for serverless APIs, see [Content safety for models curated by Azure AI in the model catalog](model-catalog-content-safety.md).
+With Azure OpenAI model deployments, you can use the default content filter or create your own content filter (described later on). Models available through **serverless APIs** have content filtering enabled by default. To learn more about the default content filter enabled for serverless APIs, see [Guidelines & controls for models curated by Azure AI in the model catalog](model-catalog-content-safety.md).
 
 ## Language support
 

articles/ai-foundry/concepts/evaluation-metrics-built-in.md

@@ -197,12 +197,12 @@ We support evaluating vulnerability towards the following types of jailbreak att
 - **Direct attack jailbreak** (also known as UPIA or User Prompt Injected Attack) injects prompts in the user role turn of conversations or queries to generative AI applications. Jailbreaks are when a model response bypasses the restrictions placed on it. Jailbreak also happens where an LLM deviates from the intended task or topic.
 - **Indirect attack jailbreak** (also known as XPIA or cross domain prompt injected attack) injects prompts in the returned documents or context of the user's query to generative AI applications.
 
-*Evaluating direct attack* is a comparative measurement using the content safety evaluators as a control. It isn't its own AI-assisted evaluator. Run `ContentSafetyEvaluator` on two different, red-teamed datasets:
+*Evaluating direct attack* is a comparative measurement using the Azure AI Content Safety evaluators as a control. It isn't its own AI-assisted evaluator. Run `ContentSafetyEvaluator` on two different, red-teamed datasets:
 
 - Baseline adversarial test dataset.
 - Adversarial test dataset with direct attack jailbreak injections in the first turn.
 
-You can do this with functionality and attack datasets generated with the [direct attack simulator](../how-to/develop/simulator-interaction-data.md#simulating-jailbreak-attacks) with the same randomization seed. Then you can evaluate jailbreak vulnerability by comparing results from content safety evaluators between the two test dataset's aggregate scores for each safety evaluator. A direct attack jailbreak defect is detected when there's presence of content harm response detected in the second direct attack injected dataset when there was none or lower severity detected in the first control dataset.
+You can do this with functionality and attack datasets generated with the [direct attack simulator](../how-to/develop/simulator-interaction-data.md#simulating-jailbreak-attacks) with the same randomization seed. Then you can evaluate jailbreak vulnerability by comparing results from Azure AI Content Safety evaluators between the two test dataset's aggregate scores for each safety evaluator. A direct attack jailbreak defect is detected when there's presence of content harm response detected in the second direct attack injected dataset when there was none or lower severity detected in the first control dataset.
 
 ### Indirect attack definition and label
 

articles/ai-foundry/concepts/model-catalog-content-safety.md

@@ -1,7 +1,7 @@
 ---
-title: Content safety for models curated by Azure AI in the model catalog
+title: Guidelines & controls for models curated by Azure AI in the model catalog
 titleSuffix: Azure AI Foundry
-description: Learn about content safety for models deployed using serverless APIs, using Azure AI Foundry.
+description: Learn about Guidelines & controls for models deployed using serverless APIs, using Azure AI Foundry.
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: conceptual
@@ -13,11 +13,11 @@ reviewer: ositanachi
 ms.custom: 
 ---
 
-# Content safety for models curated by Azure AI in the model catalog
+# Guidelines & controls for models curated by Azure AI in the model catalog
 
 [!INCLUDE [feature-preview](../includes/feature-preview.md)]
 
-In this article, learn about content safety capabilities for models from the model catalog deployed using serverless APIs.
+In this article, learn about Guidelines & controls capabilities for models from the model catalog deployed using serverless APIs.
 
 
 ## Content filter defaults

articles/ai-foundry/concepts/models-featured.md

@@ -364,5 +364,5 @@ For examples of how to use Stability AI models, see the following examples:
 - [Deploy models as serverless APIs](../how-to/deploy-models-serverless.md)
 - [Model catalog and collections in Azure AI Foundry portal](../how-to/model-catalog-overview.md)
 - [Region availability for models in serverless API endpoints](../how-to/deploy-models-serverless-availability.md)
-- [Content safety for models curated by Azure AI in the model catalog](model-catalog-content-safety.md)
+- [Guidelines & controls for models curated by Azure AI in the model catalog](model-catalog-content-safety.md)
 

articles/ai-foundry/how-to/deploy-models-gretel-navigator.md

@@ -233,11 +233,11 @@ result = client.complete(
 ```
 
 
-### Apply content safety
+### Apply Guidelines and controls
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI Content Safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI Content Safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
-The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
+The following example shows how to handle events when the model detects harmful content in the input prompt and the filter is enabled.
 
 
 ```python
@@ -477,11 +477,11 @@ The following example request shows other parameters that you can specify in the
 }
 ```
 
-### Apply content safety
+### Apply Guidelines & controls
 
-The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
+The Azure AI model inference API supports [Azure AI Content Safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI Content Safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
 
-The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
+The following example shows how to handle events when the model detects harmful content in the input prompt.
 
 
 ```json

articles/ai-foundry/how-to/develop/evaluate-sdk.md

@@ -508,7 +508,7 @@ Output:
 
 ```
 
-The result of the content safety evaluators for a query and response pair is a dictionary containing:
+The result of the Guidelines & controls evaluators for a query and response pair is a dictionary containing:
 
 - `{metric_name}` provides a severity label for that content risk ranging from Very low, Low, Medium, and High. To learn more about the descriptions of each content risk and severity scale, see [Evaluation and monitoring metrics for generative AI](../../concepts/evaluation-metrics-built-in.md).
 - `{metric_name}_score` has a range between 0 and 7 severity level that maps to a severity label given in `{metric_name}`.
@@ -570,12 +570,12 @@ We support evaluating vulnerability towards the following types of jailbreak att
 - **Direct attack jailbreak** (also known as UPIA or User Prompt Injected Attack) injects prompts in the user role turn of conversations or queries to generative AI applications.
 - **Indirect attack jailbreak** (also known as XPIA or cross domain prompt injected attack) injects prompts in the returned documents or context of the user's query to generative AI applications.
 
-*Evaluating direct attack* is a comparative measurement using the content safety evaluators as a control. It isn't its own AI-assisted metric. Run `ContentSafetyEvaluator` on two different, red-teamed datasets:
+*Evaluating direct attack* is a comparative measurement using the Azure AI Content Safety evaluators as a control. It isn't its own AI-assisted metric. Run `ContentSafetyEvaluator` on two different, red-teamed datasets:
 
 - Baseline adversarial test dataset.
 - Adversarial test dataset with direct attack jailbreak injections in the first turn.
 
-You can do this with functionality and attack datasets generated with the [direct attack simulator](./simulator-interaction-data.md) with the same randomization seed. Then you can evaluate jailbreak vulnerability by comparing results from content safety evaluators between the two test dataset's aggregate scores for each safety evaluator. A direct attack jailbreak defect is detected when there's presence of content harm response detected in the second direct attack injected dataset when there was none or lower severity detected in the first control dataset.
+You can do this with functionality and attack datasets generated with the [direct attack simulator](./simulator-interaction-data.md) with the same randomization seed. Then you can evaluate jailbreak vulnerability by comparing results from Azure AI Content Safety evaluators between the two test dataset's aggregate scores for each safety evaluator. A direct attack jailbreak defect is detected when there's presence of content harm response detected in the second direct attack injected dataset when there was none or lower severity detected in the first control dataset.
 
 *Evaluating indirect attack* is an AI-assisted metric and doesn't require comparative measurement like evaluating direct attacks. Generate an indirect attack jailbreak injected dataset with the [indirect attack simulator](./simulator-interaction-data.md) then run evaluations with the `IndirectAttackEvaluator`.
 

articles/ai-foundry/how-to/develop/simulator-interaction-data.md

@@ -408,7 +408,7 @@ We support evaluating vulnerability towards the following types of jailbreak att
 - **Direct attack jailbreak** (also known as UPIA or User Prompt Injected Attack) injects prompts in the user role turn of conversations or queries to generative AI applications.
 - **Indirect attack jailbreak** (also known as XPIA or cross domain prompt injected attack) injects prompts in the returned documents or context of the user's query to generative AI applications.
 
-*Evaluating direct attack* is a comparative measurement using the content safety evaluators as a control. It isn't its own AI-assisted metric. Run `ContentSafetyEvaluator` on two different, red-teamed datasets generated by `AdversarialSimulator`:
+*Evaluating direct attack* is a comparative measurement using the Azure AI Content Safety evaluators as a control. It isn't its own AI-assisted metric. Run `ContentSafetyEvaluator` on two different, red-teamed datasets generated by `AdversarialSimulator`:
 
 - Baseline adversarial test dataset using one of the previous scenario enums for evaluating Hateful and unfair content, Sexual content, Violent content, Self-harm-related content.
 - Adversarial test dataset with direct attack jailbreak injections in the first turn:

articles/ai-foundry/how-to/evaluation-github-action.md

@@ -17,7 +17,7 @@ author: lgayhardt
 
 This GitHub Action enables offline evaluation of AI models and agents within your CI/CD pipelines. It's designed to streamline the evaluation process, allowing you to assess model performance and make informed decisions before deploying to production.
 
-Offline evaluation involves testing AI models and agents using test datasets to measure their performance on various quality and safety metrics such as fluency, coherence, and content safety. After you select a model in the [Azure AI Model Catalog](https://azure.microsoft.com/products/ai-model-catalog?msockid=1f44c87dd9fa6d1e257fdd6dd8406c42) or [GitHub Model marketplace](https://github.com/marketplace/models), offline pre-production evaluation is crucial for AI application validation during integration testing. This process allows developers to identify potential issues and make improvements before deploying the model or application to production, such as when creating and updating agents.
+Offline evaluation involves testing AI models and agents using test datasets to measure their performance on various quality and safety metrics such as fluency, coherence, and appropriateness. After you select a model in the [Azure AI Model Catalog](https://azure.microsoft.com/products/ai-model-catalog?msockid=1f44c87dd9fa6d1e257fdd6dd8406c42) or [GitHub Model marketplace](https://github.com/marketplace/models), offline pre-production evaluation is crucial for AI application validation during integration testing. This process allows developers to identify potential issues and make improvements before deploying the model or application to production, such as when creating and updating agents.
 
 [!INCLUDE [features](../includes/evaluation-github-action-azure-devops-features.md)]
 

articles/ai-foundry/how-to/fine-tune-serverless.md

@@ -754,7 +754,7 @@ The training data used is the same as demonstrated in the SDK notebook. The CLI
 
 ## Content filtering
 
-Models deployed as a service with pay-as-you-go billing are protected by Azure AI Content Safety. When deployed to real-time endpoints, you can opt out of this capability. With Azure AI content safety enabled, both the prompt and completion pass 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. Learn more about [Azure AI Content Safety](../concepts/content-filtering.md).
+Models deployed as a service with pay-as-you-go billing are protected by Azure AI Content Safety. When deployed to real-time endpoints, you can opt out of this capability. With Azure AI Content Safety enabled, both the prompt and completion pass 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. Learn more about [Azure AI Content Safety](../concepts/content-filtering.md).
 
 
 ## Next steps