# Model Scanner

Model Scanner analyzes Machine Learning Models to identify malware, vulnerabilities, and integrity issues.

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

Model Scanner provides users with the freedom to deploy and run a model scanning tool on their infrastructure, whether it be on physical servers, cloud services, or in a secure, isolated environment without internet connectivity (air-gapped). This level of control is valuable for organizations with specific security, compliance, or operational requirements.

Model Scanner deployment types are:

- [Model Scanner SaaS](/docs/products/model-scanner/saas/overview): Uses HiddenLayer's AISec Platform Model Scanner
- [Model Scanner Self-Hosted](/docs/products/model-scanner/cli/overview): Runs the Model Scanner CLI container in your environment; self-hosted containers are available as:


See [Feature Comparison](/docs/products/model-scanner/feature_comparison) for a comparison of the different Model Scanner offerings.

Release Notes
Read the latest [Model Scanner release notes](/docs/products/model-scanner/releasenotes).

## Additional Information

- HiddenLayer Model Scanner - YouTube Video
- HiddenLayer Model Scanner - Enhance Model Security
- HiddenLayer Model Scanner - Innovation Hub
- MITRE ATLAS: The Intersection of Cybersecurity and AI | HiddenLayer
- Weaponizing ML Models with Ransomware | HiddenLayer
- Machine Learning is the New Launchpad for Ransomware | HiddenLayer
- Pickle Files: The New ML Model Attack Vector | HiddenLayer
- Machine Learning Models are Code | HiddenLayer