# HiddenLayer Product Documentation

HiddenLayer provides security for AI through its AI Security Platform. The Platform provides detection and response for Generative AI and traditional AI models to detect prompt injections, adversarial AI attacks, and digital supply chain vulnerabilities. The Platform delivers an automated and scalable defense tailored for Generative AI, enabling fast deployment and proactive responses to attacks without necessitating access to private data or models.

## HiddenLayer Products

AI Security Platform Console
AI Security Platform Console is HiddenLayer's SaaS offering that provides a seamless experience for protecting large language models. The Platform Console offers Security Operations, Data Science, and ML Operations teams visibility and protection against adversarial machine learning attacks, embedded malicious code, vulnerabilities, exploits, and integrity issues that put the company and its intellectual property at risk.

br
HiddenLayer’s AI Security Platform consists of a suite of products that provide comprehensive protection through the entire MLOps development and production lifecycle. The AI Security Platform offers Security Operations, Data Science, and ML Operations teams visibility and protection against adversarial machine learning attacks, embedded malicious code, vulnerabilities, exploits, and integrity issues that puts the company and its intellectual properties at risk.

br
Model Scanner
Model Scanner analyzes Machine Learning Models to identify hidden cybersecurity risks and threats such as malware, vulnerabilities, and integrity issues.

br
Its advanced scanning engine is built to analyze your machine learning models, meticulously inspecting each layer and component to detect possible signs of malicious activity, including malware, tampering, and backdoors.

br
Model Scanner is available as SaaS, API, and CLI.

br
AI Detection & Response
AI Detection & Response (AIDR) is a real-time input and output monitor for hosted or custom LLMs.

br
AIDR detects malicious input prompts and undesired output, and can block content from being sent to the LLM or returned to the user.

br
It has different modes of operation which can be flexibly employed, depending on the architecture already in place and the desired level of integration.