Liaison statement
LS on SG17 new work item XSTR.sem-AIA: “Technical Report: Security evaluation methods for artificial intelligence agent”
Additional information about IETF liaison relationships is available on the
IETF webpage
and the
Internet Architecture Board liaison webpage.
| State | Posted |
|---|---|
| Submitted Date | 2026-02-02 |
| From Group | ITU-T-SG-17 |
| From Contact | tsbsg17@itu.int |
| To Group | SEC |
| To Contacts | Paul Wouters <paul.wouters@aiven.io> Deb Cooley <debcooley1@gmail.com> |
| Cc | The IETF Chair <chair@ietf.org> Scott Mansfield <Scott.Mansfield@Ericsson.com> Deb Cooley <debcooley1@gmail.com> Paul Wouters <paul.wouters@aiven.io> |
| Response Contact | arnaud.taddei@broadcom.com jhnah@etri.re.kr gaofeng149@chinaunicom.cn |
| Technical Contact | arnaud.taddei@broadcom.com |
| Purpose | For information |
| Attachments | Output - Proposal for new work item XSTR.sem-AIA: Security evaluation methods for artificial intelligence agent |
| Body |
ITU-T SG17 is pleased to inform you that SG17 established a new work item: draft new ITU-T Technical Report XSTR.sem-AIA: “Technical Report: Security evaluation methods for artificial intelligence agent” (SG17-TD181-R1/WP4 - Attached) at the ITU-T SG17 plenary meeting (Geneva, 3-11 December 2025) Scope This technical report provides a thorough guide for evaluating the security of AI agents. Its goal is to strengthen the security assurance of AI agents by delivering systematic guidance for security assessment. This technical report primarily focuses on: – Defining security evaluation indicators for the capabilities of AI agents, including perception & cognition, planning, memory, and action; – Providing recommended testing methods corresponding to each security indicator. Summary The purpose of this technical report is to provide guidelines for evaluating the security of AI agents. The technical report is intended to assist AI agent providers achieving the security evaluation methods for AI agents, get an insight into potential security vulnerabilities within AI agents. It is helpful to enable early detection of security weaknesses, reduce the costs of security enhancement, and reinforce the security assurance for AI agents. More information about the new draft Technical Report could be found in the attachment. ITU-T SG17 would appreciate continuous close collaboration with ITU-T SG13, SG20, SG21, ETSI SAI, ISO/IEC JTC1/SC 42, ISO/IEC JTC1/SC 27, IETF and CEN/CENELEC TC21, and exchange of information on AI agents’ security related activities. |