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.
Red teaming, capability evaluations, adversarial testing, and performance verification.
Also in Risk & Assurance
Before running an AI system in the real world, it is important to perform system-level simulation through an ethical digital twin running on a simulation infrastructure to understand the behaviors of the AI system and assess ethical risks in a cost-effective way. Digital twin [102] was introduced by NASA as a digital representation of a real system used in lab-testing activities. The digital twin of an AI system could be used to represent the behaviors of the AI system and forecast change impacts. The ethical digital twin can also be used during operation of the AI system to assess the system’s runtime behaviors and decisions based on the simulation model using the real-time data. The assessment results can be sent back to alert the system or user before the unethical behavior or decision takes effect
Vehicle manufacturers can use the ethical digital twin to explore the limits of autonomous vehicles based on the collected real-time data, such as NVIDIA DRIVE Sim115 and rfPro.116
Reasoning
Simulation infrastructure monitors system behaviors and detects ethical risks pre- and post-deployment.
Governance Patterns
The governance for RAI systems can be defined as the structures and processes that are employed to ensure that the development and use of AI systems meet AI ethics principles. According to the structure of Shneiderman [104], governance can be built at three levels: industry level, organization level, and team level.
2.1 Oversight & AccountabilityGovernance Patterns > Industry-level governance patterns
3.1 Legal & RegulatoryGovernance Patterns > Organization-level governance patterns
2.1 Oversight & AccountabilityGovernance Patterns > Team-level governance patterns
2.1.2 Roles & AccountabilityProcess Patterns
The process patterns are reusable methods and best practices that can be used by the development team during the development process.
2.4.2 Design StandardsProcess Patterns > Requirement Engineering
2.4 Engineering & DevelopmentResponsible AI Pattern Catalogue: A Collection of Best Practices for AI Governance and Engineering
Lu, Qinghua; Zhu, Liming; Xu, Xiwei; Whittle, Jon; Zowghi, Didar; Jacquet, Aurelie (2024)
Responsible Artificial Intelligence (RAI) is widely considered as one of the greatest scientific challenges of our time and is key to increase the adoption of Artificial Intelligence (AI). Recently, a number of AI ethics principles frameworks have been published. However, without further guidance on best practices, practitioners are left with nothing much beyond truisms. In addition, significant efforts have been placed at algorithm level rather than system level, mainly focusing on a subset of mathematics-amenable ethical principles, such as fairness. Nevertheless, ethical issues can arise at any step of the development lifecycle, cutting across many AI and non-AI components of systems beyond AI algorithms and models. To operationalize RAI from a system perspective, in this article, we present an RAI Pattern Catalogue based on the results of a multivocal literature review. Rather than staying at the principle or algorithm level, we focus on patterns that AI system stakeholders can undertake in practice to ensure that the developed AI systems are responsible throughout the entire governance and engineering lifecycle. The RAI Pattern Catalogue classifies the patterns into three groups: multi-level governance patterns, trustworthy process patterns, and RAI-by-design product patterns. These patterns provide systematic and actionable guidance for stakeholders to implement RAI. © 2024 Copyright held by the owner/author(s).
Verify and Validate
Testing, evaluating, auditing, and red-teaming the AI system
Deployer
Entity that integrates and deploys the AI system for end users
Measure
Quantifying, testing, and monitoring identified AI risks
Primary
7 AI System Safety, Failures & Limitations