New IEEE Standard - Active.
Test specifications with a set of indicators for common corruption and adversarial attacks, which can be used to evaluate the robustness of artificial intelligence-based image recognition services are provided in this standard. Robustness attack threats and establishes an assessment framework to evaluate the robustness of artificial intelligence-based image recognition service under various settings are also specified in this standard.
This standard provides test specifications with a set of indicators for interference and adversarial attacks that can be used to evaluate the robustness of artificial intelligence (AI)-based image recognition services. This standard specifies robustness requirements and establishes an assessment framework to evaluate the robustness of AI-based image recognition services under various settings.
The purpose of this standard is to guide individuals and organizations who provide, develop, or use AI-based image recognition services in testing and evaluating these services and in improving the robustness of these services. 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.
SDO | IEEE: Institute of Electrical and Electronics Engineers |
Document Number | 3129 |
Publication Date | June 2, 2023 |
Language | en - English |
Page Count | 34 |
Revision Level | |
Supercedes | |
Committee | Artificial Intelligence Standards Committee |