|
Work item:
|
TR.se-ai
|
|
Subject/title:
|
Technical Report: Security Evaluation on Artificial Intelligence Technology in ICT
|
|
Status:
|
[Carried to next study period]
|
|
Approval process:
|
Agreement
|
|
Type of work item:
|
Technical report
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
-
|
|
Liaison:
|
ITU-T SG13, ISO/IEC JTC 1/SC 27, ISO/IEC JTC 1/SC 42
|
|
Supporting members:
|
China, Alibaba, China Mobile, Soonchunhyang University
|
|
Summary:
|
Evaluating the security of AI technology is a crucial step in achieving technological optimization and risk management, thereby promoting the development of AI technology towards a more mature and responsible trajectory. The evaluation of AI security encompasses a range of indicators. However, there is no unified standards for AI security assessment matrix and clear assessment methods, which might cause lack of objectivity, effectiveness and operability in application. This technical report presents an AI security evaluation framework including evaluation categories (data, model, and environment) and evaluation sub-categories for each assessment categories. It also presents security evaluation items and related evaluation methods for data, models, and environments, providing conclusive evidence and reference for evaluating the security of AI technology. AI practitioners can use the knowledge in this report to assess the features and levels of certain security items or sub-categories of a certain component of AI technology or system. This technical report can assist AI practitioners in identifying existing issues, making improvements, and determining the most suitable scenarios for AI technology.
|
|
Comment:
|
incubation queue
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2024-03-11 12:43:22
|
|
Last update:
2024-09-03 10:50:17
|
