You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/defender-for-cloud/ai-onboarding.md
+6-8Lines changed: 6 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,13 +1,13 @@
1
1
---
2
-
title: Onboard threat protection for AI workloads
2
+
title: Enable threat protection for AI workloads (preview)
3
3
description: Learn how to enable threat protection for AI workloads on your Azure subscription for Microsoft Defender for Cloud.
4
4
ms.topic: install-set-up-deploy
5
5
ms.date: 05/05/2024
6
6
---
7
7
8
-
# Onboard threat protection for AI workloads
8
+
# Enable threat protection for AI workloads (preview)
9
9
10
-
Threat protection for AI workloads in Microsoft Defender for Cloud assists you in the identification and response process in real time, for security issues that might exist in your generative AI applications.
10
+
Threat protection for AI workloads in Microsoft Defender for Cloud protects AI workloads on an Azure subscription by providing insights to threats that might affect your generative AI applications.
11
11
12
12
> [!IMPORTANT]
13
13
> Threat protection for AI workloads is currently in preview.
@@ -25,9 +25,7 @@ Threat protection for AI workloads in Microsoft Defender for Cloud assists you i
25
25
26
26
## Enroll in the limited preview
27
27
28
-
To get started, you must [sign up](https://aka.ms/D4AI/PublicPreviewAccess) and be accepted to the limited preview.
29
-
30
-
Once accepted, you can onboard threat protection for AI workloads in Defender for Cloud to provide threat protection for AI workloads in your Azure environment.
28
+
To get started, you must [sign up](https://aka.ms/D4AI/PublicPreviewAccess) and be accepted to the limited preview, you can start onboarding threat protection for AI workloads.
31
29
32
30
1. Fill out the [registration form](https://aka.ms/D4AI/PublicPreviewAccess).
33
31
@@ -37,7 +35,7 @@ If you're accepted into the limited preview, you can enable threat protection fo
37
35
38
36
## Enable threat protection for AI workloads
39
37
40
-
Threat protection for AI workloads on an Azure subscription provides insights to threats that might affect your generative AI applications.
38
+
Enable threat protection for AI workloads.
41
39
42
40
1. Sign in to the [Azure portal](https://portal.azure.com).
43
41
@@ -47,7 +45,7 @@ Threat protection for AI workloads on an Azure subscription provides insights to
47
45
48
46
1. Select the relevant Azure subscription.
49
47
50
-
1. On the Defender plans page, toggle the AI Workloads plan to **On**.
48
+
1. On the Defender plans page, toggle the AI workloads to **On**.
51
49
52
50
:::image type="content" source="media/ai-onboarding/enable-ai-workloads-plan.png" alt-text="Screenshot that shows you how to toggle threat protection for AI workloads to on." lightbox="media/ai-onboarding/enable-ai-workloads-plan.png":::
Copy file name to clipboardExpand all lines: articles/defender-for-cloud/ai-security-posture.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -26,7 +26,7 @@ Defenders for Cloud automatically and continuously discover deployed AI workload
26
26
27
27
- Azure OpenAI Service
28
28
- Azure Machine Learning
29
-
- Amazon Bedrock.
29
+
- Amazon Bedrock
30
30
31
31
Defender for Cloud can also discover vulnerabilities within generative AI library dependencies such as TensorFlow, PyTorch, and Langchain, by scanning source code for Infrastructure as Code (IaC) misconfigurations and container images for vulnerabilities. Regularly updating or patching the libraries can prevent exploits, protecting generative AI applications and maintaining their integrity.
Copy file name to clipboardExpand all lines: articles/defender-for-cloud/ai-threat-protection.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,7 +10,7 @@ author: Elazark
10
10
11
11
# Overview - AI threat protection
12
12
13
-
Threat protection for AI workloads in Microsoft Defender for Cloud provides assists you in the identification and response process in real time, for security issues that might exist in your generative AI applications.
13
+
Threat protection for AI workloads in Microsoft Defender for Cloud continually identifies threats to generative AI applications in real time and assists in the response process, for security issues that might exist in generative AI applications.
14
14
15
15
> [!IMPORTANT]
16
16
> Threat protection for AI workloads is currently in preview.
@@ -25,7 +25,7 @@ Defender for Cloud's AI threat protection integrates with [Azure AI Content Safe
25
25
26
26
## Defender XDR integration
27
27
28
-
Defenders for Cloud's threat protection for AI workloads security alerts are integrated into[Defender XDR](concept-integration-365.md), enabling security teams to centralize alerts on AI workloads within the Defender XDR portal.
28
+
Threat protection for AI workloads integrates with[Defender XDR](concept-integration-365.md), enabling security teams to centralize alerts on AI workloads within the Defender XDR portal.
29
29
30
30
Security teams can correlate AI workloads alerts and incidents within the Defender XDR portal, and gain an understanding of the full scope of an attack, including malicious activities associated with their generative AI applications from the XDR dashboard.
31
31
@@ -35,5 +35,5 @@ To use threat protection for AI workloads, you must enroll in the limited public
35
35
36
36
## Related content
37
37
38
-
-[Onboard threat protection for AI workloads (Preview)](ai-onboarding.md).
38
+
-[Enable threat protection for AI workloads (preview) (Preview)](ai-onboarding.md).
39
39
-[Alerts for AI workloads](alerts-reference.md#alerts-for-ai-workloads)
0 commit comments