Guardian by Protect AI enables enterprise-level scanning, enforcement, and management of model security to block unsafe models and keep your ML supply chain secure. Guardian scans both third and first-party models for security threats before utilization, adding a critical layer of security to ML model development and deployment. It integrates easily with existing MLOps workflows to keep pace with AI-driven innovation. Guardian ensures only secure and compliant models are utilized in enterprise networks with secure gateways and configurable policies. Guardian’s proprietary vulnerability scanners detect malicious code in new and existing AI/ML artifacts saved in popular ML storage formats. It includes executive level dashboards that aggregate information on what open source models are being used, if they are secure, who created them, how they are licensed, and more. Guardian integrates with Protect AI’s visibility product, Radar, to understand AI/ML threat surfaces. Guardian supports Pytorch, Tensorflow, XGBoost, Keras, and other frameworks. Guardian includes policies for model acceptance or rejection, enforcing checks for model origin, malicious code, safe storage formats, and OSS licensing. Guardian's Scanner API can be embedded in development and deployment pipelines to scan models before distribution, ensuring safety.
