Skip to content

[WAF] Update Firewall for AI #21616

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 11, 2025
Merged

[WAF] Update Firewall for AI #21616

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions src/content/docs/security/analytics.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,8 @@ Security analytics shows information about all incoming HTTP requests or only ab

Use Security analytics as your starting point to understand and analyze traffic patterns, and to create security rules based on the filters you applied.

Security analytics is available in **Security** > **Analytics**.

## Traffic

The **Traffic** tab displays information about all incoming HTTP requests for your domain, including requests not handled by Cloudflare security products.
Expand Down
2 changes: 2 additions & 0 deletions src/content/docs/security/rules.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,8 @@ description: Security rules perform security actions on incoming requests that m

Security rules perform security-related actions on incoming requests that match specified filters. Rules are evaluated and executed in order, from first to last.

Security rules are available in **Security** > **Security rules**.

## Security rules

The **Security rules** tab includes a list of different types of rules configured in your domain / zone to protect your applications and resources.
Expand Down
9 changes: 7 additions & 2 deletions src/content/docs/waf/detections/firewall-for-ai.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,9 +26,14 @@ Firewall for AI is available in closed beta to Enterprise customers proxying tra

<Tabs syncKey="dashPlusAPI"> <TabItem label="Dashboard">

:::note
Firewall for AI is only available in the new [application security dashboard](/security/), currently in beta for users that opt in to the new user interface.
:::

1. Log in to the [Cloudflare dashboard](https://dash.cloudflare.com/), and select your account and domain.
2. Go to **Security** > **Settings**.
3. Under **Incoming traffic detections**, turn on **Firewall for AI**.
3. Under **Web application exploits**, select **Manage detections**.
4. In **Firewall for AI**, select **Enable**.

</TabItem> <TabItem label="API">

Expand All @@ -55,7 +60,7 @@ curl "https://<YOUR_HOSTNAME>/api/v1/" \

The PII category for this request would be `EMAIL_ADDRESS`.

Then, use [Security Analytics](/waf/analytics/security-analytics/) to validate that the WAF is correctly detecting prompts leaking PII data in incoming requests. Filter data by the `cf-llm` managed endpoint label and review the detection results on your traffic.
Then, use [Security Analytics](/waf/analytics/security-analytics/) in the new application security dashboard to validate that the WAF is correctly detecting prompts leaking PII data in incoming requests. Filter data by the `cf-llm` managed endpoint label and review the detection results on your traffic.

Alternatively, create a WAF custom rule like the one described in the next step using a _Log_ action. This rule will generate [security events](/waf/analytics/security-events/) that will allow you to validate your configuration.

Expand Down