Cisco Releases Open Source Tool for AI Model Provenance - SecurityWeek

Cisco has announced the release of an open source tool called Model Provenance Kit, designed to help organizations address risks related to poisoned models, regulatory issues, supply chain integrity, and incident response. The tool was unveiled by the company's security division and is intended to provide a framework for tracking the provenance of AI models throughout their lifecycle.

The Model Provenance Kit allows users to record metadata about model creation, training data sources, and modifications. It operates as an open source project, enabling community contributions and audits. Cisco stated that the tool aims to reduce the risk of supply chain attacks and improve transparency in AI deployments. The announcement did not specify a release date but indicated the tool is available now.

The release comes amid growing concerns over AI model poisoning and supply chain vulnerabilities. Cisco, traditionally known for networking hardware, has been expanding its cybersecurity portfolio. The Model Provenance Kit is positioned as a practical solution for organizations seeking to comply with emerging AI regulations and best practices for model governance.