Details of 'DTR/SAI-003' Work Item

	Work Item Reference	ETSI Doc. Number	STF	Technical Body in Charge		Download Standard
	DTR/SAI-003	TR 104 031		SAI
	Current Status (Click to View Full Schedule)	Latest Version	Cover Date	Standstill		Creation Date
	Deliverable published (2024-02-09)	1.1.1	2024-02-09	View Standstill Information		2023-11-21
	Rapporteur	Technical Officer		Harmonised Standard
	Chonggang Wang	Kim Nordström		No
Title	Securing Artificial Intelligence (SAI); Collaborative Artificial Intelligence Collaborative Artificial Intelligence
Scope and Field of Application	This work item covers security aspects of pervasive and collaborative artificial intelligence (AI) (e.g., federated learning, transfer learning, distributed reinforcement learning, decentralized machine learning), where multiple AI agents are pervasively distributed in different places but interact with each other to work on the same or different AI tasks. These AI agents exchange AI models and/or inferred knowledge. The work item investigates use cases of security for pervasive and collaborative AI, and analyzes potential security concerns such as trust and communications among those AI agents. Then the work item provides technical recommendations on approaches to mitigate these issues including their limitations.
Supporting Organizations	THALES, Huawei Tech.(UK) Co.. Ltd, NCSC, BT plc, InterDigital, Inc.

	Keywords	Projects	Clusters	Frequencies	Mandates	Directives
	artificial intelligence Model trust		Security
Official Journal
Remarks	2024-01-23 nordstromkim Final draft for approval proposal in contribution SAI(23)000018 was Accepted by SAI 2023-12-15 mouqueta Draft contributed - V 0.0.1 contributed for Decision in SAI(23)000018 as Final draft for approval 2023-12-15 mouqueta A new draft is uploaded - V 0.0.1 with status: Final draft for approval 2023-12-04 Scott Cadzow TB adoption of WI SAI, see contribution SAI(23)001014 2023-11-21 CADZOW WI proposed to TB SAI_TC, see contribution SAI(23)001014