• Content Type

Standard for Robustness Testing and Evaluation of Artificial Intelligence (AI)-based Image Recognition Service

Last updated: 7 Jan 2025

Development Stage

Pre-draft

Draft

Published

2 Jun 2023
pre-draft

Scope

This standard provides test specifications with a set of indicators for interference and adversarial attacks, which can be used to evaluate the robustness of Artificial Intelligence-based Image Recognition services. This standard specifies robustness requirements and establishes an assessment framework to evaluate the robustness of Artificial Intelligence-based Image Recognition service under various settings. ©IEEE 2022. All rights reserved.

Purpose

The purpose of this standard is to guide individuals and organizations who provide, develop, or use Artificial Intelligence based Image Recognition to test and evaluate the service and improve the robustness of the service. It is also applicable to guide third-party evaluation laboratories to test and evaluate the robustness of the service by applying standards based testing to score individual algorithmic implementations. ©IEEE 2022. All rights reserved.

External Links

More information
[site_reviews_summary assigned_posts=”post_id” hide=”bars,if_empty” text=”{rating} out of {max} stars ({num} reviews)”]

Let the community know

Categorisation

Domain: Horizontal
Scope: AI-specific
Topic: Robustness, Security and resilience
Application: Computer vision - Image recognition
Type: Measurement and test methods, Product and performance requirements

Key Information

Organisation: IEEE The Institute of Electrical and Electronics Engineers, Inc.
Share on XShare on LinkedIn

Discussion

You must be logged in to contribute to the discussion

Login

[check_original_title]