HiddenLayer provides integrations with various third-party products and processes.
Integrations are a key part of your organization’s security and streamline your data flow. From protecting your models, viewing the results, and interacting with HiddenLayer’s API, these integrations are provided to improve your efficiency and enhance your decision-making capabilities.
The Model Scanner and AI Detection and Response (AIDR) can be leveraged in your cloud environment.
| Name | Description | Links |
|---|---|---|
| Model Scanner | HiddenLayer Model Scanner is available on several cloud provider marketplaces. Model Scanner prevents security issues by detecting malicious code in your AI models and ensures your AI models are free from adversarial code. | |
| AI Detection and Response | HiddenLayer AI Detection and Response (AIDR) is available on several cloud provider marketplaces. AIDR provides real-time cybersecurity protection for Generative AI by safeguarding against inference attacks, evasion, and model theft. |
HiddenLayer product integrations work with tools you use in your workflows.
| Name | Description | Links |
|---|---|---|
| Azure DevOps Task | Integrate HiddenLayer’s Model Scanner into your continuous integration (CI) process with HiddenLayer’s Azure DevOps task. | Azure Marketplace |
| Databricks Unity Catalog | Adds scanning to your Databricks MLOps workflow. The integration submits models registered with Unity Catalog and MLFlow to the HiddenLayer API for scanning. The plugin will apply tags to the model indicating the scan results allowing you to determine promotion and removal remediation actions if necessary. | Databricks Unity Catalog |
| HiddenLayer Model Scanner GitHub Action (SaaS) | Integrate model scanning into your continuous integration (CI) process with HiddenLayer's GitHub Actions (GHA) integration. This action can scan your models that are stored in a repository. This uses the HiddenLayer Model Scanner CLI and scans the model inside the GitHub Action. | GitHub |
| HiddenLayer Local Model Scanner GitHub Action (CLI) | Integrate model scanning into your continuous integration (CI) process with HiddenLayer’s GitHub Actions (GHA) integration. This action can scan your models that are stored in a repository or on Amazon S3. This uses the HiddenLayer SaaS Model Scanner, which uploads the model to the HiddenLayer SaaS environment. | GitHub |
| Jenkins Plugin | Adds scanning to your Jenkins pipelines. The plugin allows you to use your Jenkins pipeline to submit models to the HiddenLayer API for scanning. | Jenkins Plugin |
| JFrog Artifactory | Adds scanning to your Artifactory workflow. The plugin submits models downloaded from a Hugging Face repository to the HiddenLayer API for scanning. The plugin will block the download if the model is flagged as Unsafe (malicious). | JFrog Artifactory GitHub |
HiddenLayer integrates with tools you use to ingest output data, like SIEM.
| Name | Description | Links |
|---|---|---|
| Azure Sentinel | HiddenLayer provides an integration with Microsoft Sentinel to send AIDR conviction data for alerting and processing. | |
| Custom Webhooks | Allow users to connect HiddenLayer runtime detections with any HTTP receiver complete with customized headers. |
HiddenLayer provides different software development kits (SDKs) so you can interact with HiddenLayer’s API.
| Name | Description | Links |
|---|---|---|
| Python SDK | Provides a simple and efficient way to interact with the HiddenLayer API. Developers can easily protect models without having to write complex code or manage the underlying infrastructure. | GitHub |
| TypeScript SDK | Provides a set of tools to interact with the HiddenLayer API. This can be used in both Node.js and browser environments. | GitHub |
| Java SDK | Provides a set of tools to interact with the HiddenLayer API from Java applications. | GitHub |