Skip to main content
AI Detection & Response (AIDR) is the established version of AI Runtime Security: a real-time input and output monitor for hosted or custom LLMs, deployed as container images into your own infrastructure. It detects malicious input prompts and undesired output as they flow to and from a model, and can block or redact content.
RecommendedFor new work, Agentic Runtime Security is recommended. AIDR remains fully supported; see the Agentic Runtime Security overview for a comparison.

​
Key benefits

  • Automated: Detect and respond to AI model breach attempts with a proactive defense mechanism.
  • Scalable: Get clear reporting on detected threats, empowering security teams with insight into adversarial behavior.
  • Unobtrusive: Detections are made via our platform without requiring access to models or the data that powers them.

​
Architecture and deployment modes

See Hybrid and Disconnected Modes for information about Runtime Security architecture and the different modes of deployment.
End User License AgreementUsage of this Docker Image is subject to End-User License Agreement (EULA). Before accessing or utilizing the Docker Image, please carefully review and agree to the terms and conditions outlined in the EULA provided by HiddenLayer. The EULA governs the rights, limitations, and obligations associated with the use of the Docker Image. By using the Docker Image, you indicate your acceptance of the EULA and your commitment to adhere to its provisions. If you do not agree with the terms and conditions set forth in the EULA, refrain from using the Docker Image.

​
Additional information