Reposted from CISA/DHS

The Cybersecurity and Infrastructure Security Agency, in partnership with National Security Agency, Federal Bureau of Investigation and international partners, released a Cybersecurity Information Sheet (CSI) today, “Deploying Artificial intelligence (AI) Systems Securely: Best Practices for Deploying Secure and Resilient AI Systems.”   This guide provides best practices to secure the deployment environment, validate and protect the AI system, and secure AI operation and maintenance The three goals of this joint guide are:  

1.     Improve the confidentiality, integrity, and availability of AI systems;  

2.     Assure that known cybersecurity vulnerabilities in AI systems are appropriately mitigated; and 

3.     Provide methodologies and controls to protect, detect and respond to malicious activity against AI systems and related data and services. 

The CSI is intended to support organizations that will be deploying and operating AI systems designed and developed by an external entity. It builds upon the previously released joint Guidelines for Secure AI System Development and Engaging with Artificial Intelligence.

See Original Post