CISA and Joint-Seal AI Publications
As the nation’s cyber defense agency, CISA mission sits at the intersection of strengthening cybersecurity and protecting critical infrastructure and plays a key role in advancing the Administration’s goal of ensuring that AI is safe, secure, and resilient, starting with being secure by design. This mission includes engaging with international partners surrounding global AI security, publishing actionable guidance, and promoting the adoption of best practices. Below are key publications and guidance that tie to CISA’s AI mission:
AI Cybersecurity Collaboration Playbook
The Playbook guides AI providers, developers, and adopters on voluntarily sharing AI-related cybersecurity information with CISA and partners. It encourages adoption of key practices to strengthen collective defenses against AI-related threats.
AI Red Teaming: Applying Software TEVV for AI Evaluations
Discover how AI red teaming fits into proven software evaluation frameworks to enhance safety and security.
Deploying AI Systems Securely
The National Security Agency’s Artificial Intelligence Security Center (NSA AISC), along with CISA and other U.S. and international partners, published this guidance for organizations deploying and operating externally developed AI systems.
Guidelines for secure AI system development
Guidelines for providers of any systems that use artificial intelligence (AI), whether those systems have been created from scratch or built on top of tools and services provided by others.
Software Must Be Secure by Design, and Artificial Intelligence Is No Exception
Like any software system, AI must be Secure by Design. Manufacturers of AI systems must prioritize security throughout the whole lifecycle of the product.
Engaging with artificial intelligence
The ACSC, along with CISA and other U.S. and international partners, published a paper summarizing some important threats related to AI systems and prompting organizations to consider steps they can take to engage with AI while managing risk.