Towards Communication-Efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things

2020/12/08 by Yi Liu, Ruihui Zhao, Jiawen Kang +3
Computer Science · #Adversarial Robustness in Machine Learning #Artificial intelligence #Asynchronous communication #Asynchronous learning #Cloud computing #Computer network #Computer science #Computer security #Cryptography and Data Security #Distributed computing #Edge computing #Edge device #Enhanced Data Rates for GSM Evolution #Industrial Internet #Internet of Things #Node (physics) #Overhead (engineering) #Privacy-Preserving Technologies in Data #The Internet #cs.CR #cs.DC #cs.LG

paper · pdf · doi:10.1145/3453169

arxiv created 2020/12/08 · arxiv updated 2021/11/05 · openalex publication_date 2021/12/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Federated Edge Learning (FEL) allows edge nodes to train a global deep learning model collaboratively for edge computing in the Industrial Internet of Things (IIoT), which significantly promotes the development of Industrial 4.0. However, FEL faces two critical challenges: communication overhead and data privacy. FEL suffers from expensive communication overhead when training large-scale multi-node models. Furthermore, due to the vulnerability of FEL to gradient leakage and label-flipping attacks, the training process of the global model is easily compromised by adversaries. To address these challenges, we propose a communication-efficient and privacy-enhanced asynchronous FEL framework for edge computing in IIoT. First, we introduce an asynchronous model update scheme to reduce the computation time that edge nodes wait for global model aggregation. Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes. Third, we design a cloud-side malicious node detection mechanism to detect malicious nodes by testing the local model quality. Such a mechanism can avoid malicious nodes participating in training to mitigate label-flipping attacks. Extensive experimental studies on two real-world datasets demonstrate that the proposed framework can not only improve communication efficiency but also mitigate malicious attacks while its accuracy is comparable to traditional FEL frameworks.

Citations

• Gradient-based learning applied to document recognition
• Extremal Mechanisms for Local Differential Privacy
• Federated Learning: Strategies for Improving Communication Efficiency
• Gradient Sparsification for Communication-Efficient Distributed Optimization
• QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
• Differentially Private Federated Learning: A Client Level Perspective
• Byzantine Stochastic Gradient Descent
• ATOMO: Communication-efficient Learning via Atomic Sparsification
• How To Backdoor Federated Learning
• A generic framework for privacy preserving deep learning
• Analyzing Federated Learning through an Adversarial Lens
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Stochastic Distributed Learning with Gradient Quantization and Variance Reduction
• The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost
• Abnormal Client Behavior Detection in Federated Learning
• Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection
• Why gradient clipping accelerates training: A theoretical justification for adaptivity
• Blockchain Empowered Asynchronous Federated Learning for Secure Data Sharing in Internet of Vehicles
• A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
• Federated Learning: Challenges, Methods, and Future Directions
• Data Poisoning Attacks Against Federated Learning Systems
• Learning Multiple Layers of Features from Tiny Images
• The Algorithmic Foundations of Differential Privacy
• DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation