This page is still being polished. If you have thoughts, please share them via the feedback form.
Data on this page is preliminary and may change. Please do not share or cite these figures publicly.
Cryptographic protections, access controls, and hardware security.
Also in Non-Model
Attackers may be able to reconstruct the functionality of a model13 or the data it was trained on14, by accessing a model directly (by acquiring model weights) or indirectly (by querying the model via an application or service). Attackers may also tamper with models, data or prompts during or after training, rendering the output untrustworthy. You protect the model and data from direct and indirect access, respectively, by: > implementing standard cyber security best practices > implementing controls on the query interface to detect and prevent attempts to access, modify, and exfiltrate confidential information. To ensure that consuming systems can validate models, you compute and share cryptographic hashes and/or signatures of model files (for example, model weights) and datasets (including checkpoints) as soon as the model is trained. As always with cryptography, good key management is essential.
Your approach to confidentiality risk mitigation will depend considerably on the use case and the threat model. Some applications, for example those involving very sensitive data, may require theoretical guarantees that can be difficult or expensive to apply. If appropriate, privacy-enhancing technologies (such as differential privacy or homomorphic encryption) can be used to explore or assure levels of risk associated with consumers, users and attackers having access to models and outputs.
Reasoning
Cryptographic hashing and signatures enable model integrity verification and provenance tracking.
Secure design
This section contains guidelines that apply to the design stage of the AI system development life cycle. It covers understanding risks and threat modelling, as well as specific topics and trade-offs to consider on system and model design.
2.4.2 Design StandardsSecure design > Raise staff awareness of threats and risks
System owners and senior leaders understand threats to secure AI and their mitigations. Your data scientists and developers maintain an awareness of relevant security threats and failure modes and help risk owners to make informed decisions. You provide users with guidance on the unique security risks facing AI systems (for example, as part of standard InfoSec training) and train developers in secure coding techniques and secure and responsible AI practices.
2.4.4 Training & AwarenessSecure design > Model the threats to your system
As part of your risk management process, you apply a holistic process to assess the threats to your system, which includes understanding the potential impacts to the system, users, organisations, and wider society if an AI component is compromised or behaves unexpectedly. This process involves assessing the impact of AI-specific threats and documenting your decision making.
2.2.1 Risk AssessmentSecure design > Design your system for security as well as functionality and performance
You are confident that the task at hand is most appropriately addressed using AI. Having determined this, you assess the appropriateness of your AI-specific design choices. You consider your threat model and associated security mitigations alongside functionality, user experience, deployment environment, performance, assurance, oversight, ethical and legal requirements, among other considerations.
2.4.2 Design StandardsSecure design > Consider security benefits and trade-offs when selecting your AI model
Your choice of AI model will involve balancing a range of requirements. This includes choice of model architecture, configuration, training data, training algorithm and hyperparameters. Your decisions are informed by your threat model, and are regularly reassessed as AI security research advances and understanding of the threat evolves.
2.4.2 Design StandardsSecure development
This section contains guidelines that apply to the development stage of the AI system development lifecycle, including supply chain security, documentation, and asset and technical debt management.
2.4.3 Development WorkflowsGuidelines for secure AI development
UK National Cyber Security Centre (NCSC); US Cybersecurity and Infrastructure Security Agency (CISA); National Security Agency (NSA); Federal Bureau of Investigation (FBI); Australian Signals Directorate's Australian Cyber Security Centre (ASD ACSC) (2023)
This document recommends 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. Implementing these guidelines will help providers build AI systems that function as intended, are available when needed, and work without revealing sensitive data to unauthorised parties.
Deploy
Releasing the AI system into a production environment
Deployer
Entity that integrates and deploys the AI system for end users
Manage
Prioritising, responding to, and mitigating AI risks
