Committed to connecting the world

  •  

ITU-T work programme

[2025-2028] : [SG17] : [Q7/17]

[Declared patent(s)]  - [Associated work]

Work item: X.2213 (ex X.sg-GenAI)
Subject/title: Security guidelines for generative artificial intelligence application service
Status: Determined on 2026-06-10 [Issued from previous study period]
Approval process: TAP
Type of work item: Recommendation
Version: New
Equivalent number: -
Timing: 2026-06 (Medium priority)
Liaison: ITU-T SG13, SG16, ISO/IEC JTC 1/SC 27, ISO/IEC JTC 1/SC 42
Supporting members: China, Alibaba, China Unicom, Soonchunhyang University
Summary: Nowadays, multiple powerful and versatile generative AI (GenAI) application services have been released, significantly adding convenience to our lives. The industry focuses on the rapid implementation of GenAI and utilizes the powerful capabilities of GenAI application services to achieve higher work efficiency. Generative AI technologies enable automated content creation across multiple modalities, while also raising important considerations related to security, privacy, and trustworthiness. However, GenAI application services also face various risks. There are two broad classes of risks associated with GenAI application services: risks common to AI systems in general and risks specific to GenAI application services. Similar to general AI systems, GenAI faces risks related to data and model threats. At the same time, GenAI application services face specific risks such as prompt injection attacks, prompt jailbreaking, hallucinations, API attacks, and supply chain attacks. Therefore, there is a need to analyse the risks associated with GenAI application services and provide security guidelines to mitigate the identified risks. Accordingly, this Recommendation identifies and outlines a range of potential risks and provides corresponding security guidelines that should be implemented to securely operate GenAI application services.
Comment: -
Reference(s):
  Historic references:
Contact(s):
Huifang LI, Editor
Yang CHEN, Editor
Bin LIU, Editor
Zhiqiang LI, Editor
ITU-T A.5 justification(s):
Generate A.5 drat TD
-
[Submit new A.5 justification ]
See guidelines for creating & submitting ITU-T A.5 justifications
First registration in the WP: 2024-03-11 11:49:14
Last update: 2026-06-26 12:17:58