HFedM2ND: A secure Hierarchical Federated Learning framework against poisoning attacks with lightweight multi-layer malicious-node detection
Authors:
- Lina GeLGLina Ge
- Qinglin BiQBQinglin Bi
- Sen LiSLSen Li
- Lei TianLTLei Tian
- Zhe WangZWZhe Wang
- 18 September 2026
- journal article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (61862007)
- Natural Science Foundation of Guangxi Province (2025GXNSFBA069303)
This publication has 17 references indexed in Scilit:
- HFLMLD: Enhancing Robustness in Hierarchical Federated Learning With Multiple Layer DefensesIEEE Internet of Things Journal, 2025
- Analysis of deep learning under adversarial attacks in hierarchical federated learningHigh-Confidence Computing, 2025
- Survey: federated learning data security and privacy-preserving in edge-Internet of ThingsArtificial Intelligence Review, 2024
- Towards robust and privacy-preserving federated learning in edge computingComputer Networks, 2024
- FedDMC: Efficient and Robust Federated Learning via Detecting Malicious ClientsIEEE Transactions on Dependable and Secure Computing, 2024
- Blockchain-Based Trustworthy and Efficient Hierarchical Federated Learning for UAV-Enabled IoT NetworksIEEE Internet of Things Journal, 2024
- MITDBA: Mitigating Dynamic Backdoor Attacks in Federated Learning for IoT ApplicationsIEEE Internet of Things Journal, 2023
- MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clients2022
- SEAR: Secure and Efficient Aggregation for Byzantine-Robust Federated LearningIEEE Transactions on Dependable and Secure Computing, 2021
- On the Design of Federated Learning in the Mobile Edge Computing SystemsIEEE Transactions on Communications, 2021