Jump to content
Google Account
Google Account

Blue shield with white G icon.

Google's Secure AI Framework (SAIF)

The potential of AI, especially generative AI, is immense. As innovation moves forwards, the industry needs security standards for building and deploying AI responsibly. That's why we introduced the Secure AI Framework (SAIF), a conceptual framework to secure AI systems.

Six core elements of SAIF

SAIF is designed to address top-of-mind concerns for security professionals, such as AI/ML model risk management, security and privacy — helping to ensure that when AI models are implemented, they are secure by default.
Download PDF

  • Expand strong security foundations to the AI ecosystem

  • Extend detection and response to bring AI into an organisation's threat universe

  • Automate defences to keep pace with existing and new threats

  • Harmonise platform-level controls to ensure consistent security across the organisation

  • Adapt controls to adjust mitigations and create faster feedback loops for AI deployment

  • Contextualise AI system risks in surrounding business processes

Enabling a safer ecosystem

We’re excited to share the first steps in our journey to build a SAIF ecosystem across governments, businesses and organisations to advance a framework for secure AI deployment that works for all.
Graphic showing a pink grid sending prompts to a screen.

Introducing SAIF.Google: Secure AI starts here

SAIF.Google is a resource hub to help security professionals navigate the evolving landscape of AI security. It provides a collection of AI security risks and controls, including a 'Risk self-assessment report' to guide practitioners in understanding the risks that could affect them and how to implement SAIF in their organisations. These resources will help address the critical need to build and deploy secure AI systems in a rapidly evolving world.
Get started
Constellation graphic with blue shield with a white G in the middle, surrounded by building, padlock, profile, world and document icons.

Bringing SAIF to governments and organisations

We collaborate with governments and organisations to help mitigate AI security risks. Our work with policymakers and standards organisations such as NIST contributes to evolving regulatory frameworks. We recently highlighted SAIF's role in securing AI systems, aligning with the White House's AI commitments.
Circle with tech company logos inside.

Coalition for Secure AI: Expanding SAIF with industry allies

We are advancing this work and fostering industry support by forming the Coalition for Secure AI (CoSAI), with founding members like Anthropic, Cisco, GenLab, IBM, Intel, Nvidia and PayPal, to address critical challenges in implementing secure AI systems.

Additional resources

Common questions
about SAIF

How is Google putting SAIF into action?

Google has a long history of driving responsible AI and cybersecurity development, and we have been mapping security best practices to AI innovation for many years. Our Secure AI Framework is distilled from the body of experience and best practices that we've developed and implemented, and reflects Google's approach to building ML and generative-AI-powered apps with responsive, sustainable and scalable protections for security and privacy. We will continue to evolve and build SAIF to address new risks, changing landscapes and advancements in AI.

How can practitioners implement the framework?

See our quick guide to implementing the SAIF framework:

  • Step 1 – Understand the use
    • Understanding the specific business problem that AI will solve and the data that's needed to train the model will help drive the policy, protocols and controls that need to be implemented as part of SAIF.
  • Step 2 – Assemble the team
    • Developing and deploying AI systems, just like traditional systems, is a multidisciplinary effort.
    • AI systems are often complex and opaque, include large numbers of moving parts, rely on large amounts of data, are resource intensive, can be used to apply judgement-based decisions, and can generate novel content that may be offensive, harmful, or can perpetuate stereotypes and social biases.
    • Establish the right cross-functional team to ensure that security, privacy, risk and compliance considerations are included from the start.

  • Step 3 – Level-set with an AI primer

    • As teams embark on evaluating the business use of AI, and the various and evolving complexities, risks and security controls that apply, it is critical that all parties involved understand the basics of the AI-model-development life cycle and the design and logic of the model methodologies, including capabilities, merits and limitations.

  • Step 4 – Apply the six core elements of SAIF

    • These elements are not intended to be applied in chronological order.

Where can I find more information about SAIF and how to apply it to my business or entity?

Stay tuned! Google will continue to build and share Secure AI Framework resources, guidance and tools, along with other best practices in AI application development.

Why we support a secure AI community for everyone

As one of the first companies to articulate Al principles, we’ve set the standard for responsible Al, and it guides our product development for safety. We've advocated for and developed industry frameworks to raise the security bar and learned that building a community to advance this work is essential for success in the long term. That's why we're excited to build an SAIF community for all.