Tools and Practices for Responsible AI Engineering

TL;DR

This paper introduces two new software libraries, hydra-zen and rAI-toolbox, designed to improve responsible AI engineering by simplifying configuration, reproducibility, and robustness evaluation of AI systems.

Contribution

The paper presents novel tools that enhance responsible AI development through improved configurability, reproducibility, and robustness testing, integrating seamlessly with existing machine learning frameworks.

Findings

hydra-zen simplifies complex AI application configuration

rAI-toolbox enables scalable robustness evaluation methods

Tools demonstrate effective use in adversarial robustness and explainability tasks

Abstract

Responsible Artificial Intelligence (AI) - the practice of developing, evaluating, and maintaining accurate AI systems that also exhibit essential properties such as robustness and explainability - represents a multifaceted challenge that often stretches standard machine learning tooling, frameworks, and testing methods beyond their limits. In this paper, we present two new software libraries - hydra-zen and the rAI-toolbox - that address critical needs for responsible AI engineering. hydra-zen dramatically simplifies the process of making complex AI applications configurable, and their behaviors reproducible. The rAI-toolbox is designed to enable methods for evaluating and enhancing the robustness of AI-models in a way that is scalable and that composes naturally with other popular ML frameworks. We describe the design principles and methodologies that make these tools effective, including the use of property-based testing to bolster the reliability of the tools themselves. Finally, we demonstrate the composability and flexibility of the tools by showing how various use cases from adversarial robustness and explainable AI can be concisely implemented with familiar APIs.