An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services

TL;DR

This paper introduces an open API architecture for explainable AI in cloud services, enabling transparent feature explanations, performance evaluation, and trustworthiness assessment without revealing model internals.

Contribution

It proposes a microservice-based open API design for XAI in cloud AI, facilitating model evaluation and reproducibility while maintaining model opacity.

Findings

Architecture is cloud-agnostic and adaptable.

Data augmentation improves XAI consistency.

Open APIs enable trustworthy cloud AI explanations.

Abstract

This article presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services. Cloud AI services are widely used to develop domain-specific applications with precise learning metrics. However, the underlying cloud AI services remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud models. We can also utilize this architecture to evaluate the model performance and XAI consistency metrics showing cloud AI services trustworthiness. We collect provenance data from operational pipelines to enable reproducibility within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding model performance and XAI consistency metrics for the leading cloud vision AI services. The results confirm that the architecture, based on open APIs, is cloud-agnostic. Additionally, data augmentations result in measurable improvements in XAI consistency metrics for cloud AI services.