This standard specifies test methods for evaluating the robustness of a Natural Language Processing (NLP) service that uses machine learning. Models of NLP generally feature an input space being discrete and an output space being almost infinite in some tasks. The robustness of the NLP service is affected by various perturbations including adversarial attacks. A methodology to categorize the perturbations, and test cases for evaluating the robustness of an NLP service against different perturbation categories is specified. Metrics for robustness evaluation of an NLP service are defined. NLP use cases and corresponding applicable test methods are also described.
- Sponsor Committee
- C/AISC - Artificial Intelligence Standards Committee
- Active PAR
- PAR Approval
Working Group Details
IEEE Draft Standard for Robustness Testing and Evaluation of Artificial Intelligence (AI)-based Image Recognition Service
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.