Deploying AI systems securely requires careful setup and configuration that depends on the complexity of the AI system, the resources required, and the infrastructure used.
That is why the National Security Agency’s Artificial Intelligence Security Center (NSA AISC) published the joint Cybersecurity Information Sheet Deploying AI Systems Securely in collaboration with the Cybersecurity and Infrastructure Security Agency (CISA), the Federal Bureau of Investigation (FBI), the Australian Signals Directorate’s Australian Cyber Security Centre (ASD ACSC), the Canadian Centre for Cyber Security (CCCS), the New Zealand National Cyber Security Centre (NCSC-NZ), and the United Kingdom’s National Cyber Security Centre (NCSC-UK).
AI security is a rapidly evolving area of research. Agencies, industry, and academia are discovering potential weaknesses in AI technology and techniques, which means organizations will need to update their AI systems to address the changing risks, in addition to applying traditional IT best practices to AI systems.
Rapid adoption, deployment, and use of AI capabilities can make them highly valuable targets for malicious cyber actors. Actors, who have historically used data theft of sensitive information and intellectual property to advance their interests, may seek to co-opt deployed AI systems and apply them to malicious ends.
Malicious actors targeting AI systems may use attack vectors unique to AI systems, as well as standard techniques used against traditional IT. Due to the large variety of attack vectors, defenses need to be diverse and comprehensive.
One thing organizations need to do is secure the deployment environment. They typically deploy AI systems within existing IT infrastructure. Before deployment, they should ensure the IT environment applies sound security principles, such as robust governance, a well-designed architecture, and secure configurations.
The following best practices are particularly important to apply to the AI systems and the IT environments the organization deploys them in:
Manage deployment environment governance: If an organization outside of IT is deploying or operating the AI system, work with the IT service department to identify the deployment environment and confirm it meets the organization’s IT standards.
Ensure a robust deployment environment architecture: Establish security protections for the boundaries between the IT environment and the AI system.
Harden deployment environment configurations: Apply existing security best practices to the deployment environment. This includes sandboxing the environment running ML models within hardened containers or virtual machines (VMs), monitoring the network, configuring firewalls with allow lists, and other best practices, such as those in NSA’s Top Ten Cloud Mitigation Strategies for cloud deployments.
Protect deployment networks from threats: Adopt a zero trust mindset, which assumes a breach is inevitable or has already occurred. Implement detection and response capabilities, enabling quick identification and containment of compromises.
Validate the AI system before and during use: Use cryptographic methods, digital signatures, and checksums to confirm each artifact’s origin and integrity, protecting sensitive information from unauthorized access during AI processes.
Secure exposed APIs: If the AI system exposes application programming interfaces (APIs), secure them by implementing authentication and authorization mechanisms for API access. Use secure protocols, such as HTTPS with encryption and authentication.
Actively monitor model behavior: Collect logs to cover inputs, outputs, intermediate states, and errors; automate alerts and triggers.
Click here for more on the multi-national Cybersecurity Information Sheet.

