English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As a key technology in 6G research, federated learning (FL) enablescollaborative learning among multiple clients while ensuring individual dataprivacy. However, malicious attackers among the participating clients canintentionally tamper with the training data or the trained model, compromisingthe accuracy and trustworthiness of the system. To address this issue, in thispaper, we propose a hierarchical audit-based FL (HiAudit-FL) framework, withthe aim to enhance the reliability and security of the learning process. Thehierarchical audit process includes two stages, namely model-audit andparameter-audit. In the model-audit stage, a low-overhead audit method isemployed to identify suspicious clients. Subsequently, in the parameter-auditstage, a resource-consuming method is used to detect all malicious clients withhigher accuracy among the suspicious ones. Specifically, we execute the modelaudit method among partial clients for multiple rounds, which is modeled as apartial observation Markov decision process (POMDP) with the aim to enhance therobustness and accountability of the decision-making in complex and uncertainenvironments. Meanwhile, we formulate the problem of identifying maliciousattackers through a multi-round audit as an active sequential hypothesistesting problem and leverage a diffusion model-based AI-Enabled audit selectionstrategy (ASS) to decide which clients should be audited in each round. Toaccomplish efficient and effective audit selection, we design a DRL-ASSalgorithm by incorporating the ASS in a deep reinforcement learning (DRL)framework. Our simulation results demonstrate that HiAudit-FL can effectivelyidentify and handle potential malicious users accurately, with small systemoverhead.

TrustFed: A Reliable Federated Learning Framework with Malicious-Attack Resistance