Trust-Driven and Interaction-Driven Resilient Distributed Secure Learning Algorithm and Its Application

doi:10.1109/tcns.2026.3691761

Trust-Driven and Interaction-Driven Resilient Distributed Secure Learning Algorithm and Its Application

2026-05-11

0

PRE

AI

DOI：10.1109/tcns.2026.3691761

Original

Original request for help

Save

Abstract

En 中文

This article investigates the problem of distributed nonconvex secure learning for multiagent systems in nonsecure and nontrusted environments, where only local datasets are available. To enhance the system’s security and privacy during information exchange, we propose a trust-driven and interaction-driven robust adaptive learning algorithm. Theoretical analysis demonstrates that the proposed algorithm effectively protects agent privacy while mitigating the impact of various types and arbitrary numbers of noncooperative agents, without incurring additional communication or computational overhead. Finally, experiments on the image recognition task validate the algorithm’s performance, showing that it outperforms existing methods in terms of security and privacy.

Keywords:

Adaptive learning

distributed learning

privacy preservation

resilient algorithm

trust mechanism

Trust-Driven and Interaction-Driven Resilient Distributed Secure Learning Algorithm and Its Application

Abstract

Journal

Organization

Cited Papers