Robust Intelligence AI Firewall
Robust Intelligence AI Firewall
Robust Intelligence AI Firewall Results dashboard
このページは日本語には対応しておりません。随時翻訳に取り組んでいます。翻訳に関してご質問やご意見ございましたら、お気軽にご連絡ください。
Overview
The Robust Intelligence AI Firewall is a protective layer for AI models.
The AI Firewall inspects incoming user prompts to block malicious payloads, including any that attempt prompt injection, prompt extraction, or PII detection. The AI Firewall scans LLM model output to ensure it’s free of false information, sensitive data, and harmful content. Responses that fall outside your organization’s standards are blocked from the application.
This integration monitors the AI Firewall results through the Datadog Agent. It provides users with observability of their AI security issues including metrics for allowed data points, blocked data points, and insight on why each data point was blocked.
Setup
Follow the instructions below to install and configure this check for an Agent running on a host. For containerized environments, see the Autodiscovery Integration Templates for guidance on applying these instructions.
Installation
For Agent v7.21+ / v6.21+, follow the instructions below to install the Robust Intelligence AI Firewall check on your host. See Use Community Integrations to install with the Docker Agent or earlier versions of the Agent.
Run the following command to install the Agent integration:
datadog-agent integration install -t datadog-robust-intelligence-ai-firewall==1.0.0
Configure your integration similar to core integrations. Refer to the Configuration section below for steps specific to this integration.
Configuration
Edit the robust_intelligence_ai_firewall.d/conf.yaml file in the conf.d/ folder at the root of your Agent’s configuration directory to start collecting your Robust Intelligence AI Firewall performance data.
init_config:
instances:
## @param metrics_endpoint - string - required
## The URL to Robust Intelligence AI Firewall
## internal metrics per loaded plugin in Prometheus
## format.
#
- openmetrics_endpoint: http://localhost:8080/metrics
See the sample robust_intelligence_ai_firewall.d/conf.yaml file for all available configuration options.
To configure the integration for AI Firewall running in a containerized environment, add the following annotation to pods:
apiVersion: v1
kind: Pod
# (...)
metadata:
name: '<POD_NAME>'
annotations:
ad.datadoghq.com/<CONTAINER_IDENTIFIER>.checks: |
{
"robust_intelligence_ai_firewall": {
"init_config": {},
"instances": [
{
"openmetrics_endpoint": "http://%%host%%:8080/metrics"
}
]
}
}
# (...)
Restart the Agent.
Validation
Run the Agent’s status subcommand and look for robust_intelligence_ai_firewall under the Checks section.
Data Collected
Metrics
robust_intelligence_ai_firewall.firewall_requests.count
(counter) | Number of times the firewall was called to validate request |
robust_intelligence_ai_firewall.rule_evaluated.count
(counter) | Number of times the rule was evaluated by firewall |
Service Checks
Robust Intelligence AI Firewall does not include any service checks.
Events
Robust Intelligence AI Firewall does not include any events.
Troubleshooting
Need Help? Contact Robust Intelligence Support.
