An Early-Stage Workflow Proposal for the Generation of Safe and Dependable AI Classifiers

TL;DR

This paper proposes an early-stage, adaptable workflow for generating safe and dependable AI classifiers, based on extended ONNX models, aiming to improve transparency and safety in AI development.

Contribution

It introduces a lightweight, transparent workflow for safe AI model generation that balances stability and adaptability, using extended ONNX models as a foundation.

Findings

Proposed workflow enhances safety and dependability in AI classifiers.

Use case demonstrates practical application of the workflow.

Framework is designed to be extended by third-party use cases.

Abstract

The generation and execution of qualifiable safe and dependable AI models, necessitates definition of a transparent, complete yet adaptable and preferably lightweight workflow. Given the rapidly progressing domain of AI research and the relative immaturity of the safe-AI domain the process stability upon which functionally safety developments rest must be married with some degree of adaptability. This early-stage work proposes such a workflow basing it on a an extended ONNX model description. A use case provides one foundations of this body of work which we expect to be extended by other, third party use-cases.