The National Institute of Standards and Technology has started soliciting public comments on an initial draft report on the terminology in the field of adversarial machine learning and taxonomy of mitigations and attacks.
NIST said Wednesday the terminology and the taxonomy seek to inform future practice guides and other standards for evaluating and managing the security of artificial intelligence systems through the establishment of a common language.
The agency is seeking insights on the latest attacks that threaten the current landscape of AI models, latest mitigations that are likely to withstand the test of time and new terminology that needs standardization.
Interested stakeholders could also share about the latest trends in AI technologies that intend to transform the industry or society, potential vulnerabilities related to such technologies and possible mitigations that could be developed to address such vulnerabilities.
Comments are due Sept. 30.
