mlsanityData to 7 Oct 2026

SHFL: Secure Hierarchical Federated Learning Framework for Edge Networks

arXiv 2409.15067 ↗First posted 23 Sep 2024cs.LG cs.CRcited by 0

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Federated Learning (FL) is a distributed machine learning paradigm designed for privacy-sensitive applications that run on resource-constrained devices with non-Identically and Independently Distributed (IID) data. Traditional FL frameworks adopt the client-server model with a single-level aggregation (AGR) process, where the server builds the global model by aggregating all trained local models received from client devices. However, this conventional approach encounters challenges, including susceptibility to model/data poisoning attacks. In recent years, advancements in the Internet of Things (IoT) and edge computing have enabled the development of hierarchical FL systems with a two-level AGR process running at edge and cloud servers. In this paper, we propose a Secure Hierarchical FL (SHFL) framework to address poisoning attacks in hierarchical edge networks. By aggregating trained models at the edge, SHFL employs two novel methods to address model/data poisoning attacks in the presence of client adversaries: 1) a client selection algorithm running at the edge for choosing IoT devices to participate in training, and 2) a model AGR method designed based on convex optimization theory to reduce the impact of edge models from networks with adversaries in the process of computing the global model (at the cloud level). The evaluation results reveal that compared to state-of-the-art methods, SHFL significantly increases the maximum accuracy achieved by the global model in the presence of client adversaries applying model/data poisoning attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 18 of its 41 references that are in the map. First posted on arXiv 23 Sep 2024.

Builds on

18 of 41 references.

References · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  4. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  5. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  6. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  7. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 65
  8. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  9. 2020Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computingcited by 52
  10. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 52
  11. 2021FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspectivecited by 35
  12. 2022LoMar: A Local Defense Against Poisoning Attack on Federated Learningcited by 29
6 more
  1. 2022FLCert: Provably Secure Federated Learning against Poisoning Attackscited by 29
  2. 2023Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learningcited by 29
  3. 2022Shielding Federated Learning: Robust Aggregation with Adaptive Client Selectioncited by 18
  4. 2021Covert Model Poisoning Against Federated Learning: Algorithm Design and Optimizationcited by 6
  5. 2022Studying the Robustness of Anti-adversarial Federated Learning Models Detecting Cyberattacks in IoT Spectrum Sensorscited by 5
  6. 2023GT-TSCH: Game-Theoretic Distributed TSCH Scheduler for Low-Power IoT Networkscited by 1

Built on by

Not cited yet.