درباره ما
Securing Artificial Intelligence (SAI); AI Threat Ontology and definitions
ETSI TS 104 050 V1.1.1
Organization:
ETSI - European Telecommunications Standards Institute
Year: 2025
ETSI - European Telecommunications Standards Institute
Subject: artificial intelligence
Collections
:
-
Statistics
Securing Artificial Intelligence (SAI); AI Threat Ontology and definitions
Show full item record
| contributor author | ETSI - European Telecommunications Standards Institute | |
| date accessioned | 2025-09-30T23:00:34Z | |
| date available | 2025-09-30T23:00:34Z | |
| date copyright | 2025.03 | |
| date issued | 2025 | |
| identifier other | ts_104050v010101p.pdf | |
| identifier uri | http://yse.yabesh.ir/std;jsessioutho4703177793325273135A68A10958014A0Fa/handle/yse/347723 | |
| language | English | |
| publisher | ETSI - European Telecommunications Standards Institute | |
| title | Securing Artificial Intelligence (SAI); AI Threat Ontology and definitions | en |
| title | ETSI TS 104 050 V1.1.1 | num |
| type | standard | |
| page | 28 | |
| status | Published | |
| tree | ETSI - European Telecommunications Standards Institute:;2025 | |
| contenttype | fulltext | |
| subject keywords | artificial intelligence | |
| scope | The purpose of this work item is to define what would be considered an AI threat and how it might differ from threats to traditional systems. The WI defines a common terminology for AI (aligned to CEN/ISO). The starting point that offers the rationale for this work is that currently, there is no common understanding of what constitutes an attack on AI and how it might be created, hosted and propagated. The AI Threat Ontology deliverable will seek to align terminology across the different stakeholders and multiple industries. This document will define what is meant by these terms in the context of cyber and physical security and with an accompanying narrative that should be readily accessible by both experts and less informed audiences across multiple industries. Note that this threat ontology will address AI as a system, an adversarial attacker, and a system defender. |