DT-BFL: Digital Twins for Blockchain-enabled Federated Learning in Internet of Things networks

摘要

Sixth-generation (6G) wireless networks are set to transform the Internet of Things (IoT) by enabling faster, smarter, and more connected systems. These networks will bring together a wide range of devices, including cars, robots, industrial machines, and smartphones, to support edge intelligence and real-time decision-making. Federated learning (FL) supports this shift by allowing devices to collaboratively train models without sharing raw data, which helps to protect user privacy. Despite its advantages, FL faces significant security challenges, including poisoning attacks and Byzantine clients, both of which can compromise the training process and degrade the accuracy and reliability of the global model. Although existing methods can detect malicious updates, many advanced attacks still bypass statistical defenses relying on metrics such as median and distance. Thus, developing an FL system that ensures both reliable decision-making and privacy and security guarantees in IoT networks remains a significant challenge. This study introduces a Digital Twin-driven Blockchain-enabled Federated Learning (DT-BFL) framework designed for IoT networks. The framework creates a digital representation of the IoT environment to support secure and decentralized edge intelligence using blockchain and federated learning technologies. DT-BFL is built to detect and filter out potentially poisoned model updates from malicious participants. This is achieved through a new smart contract-enabled decentralized aggregation method called Local Updates Purify (LUP). LUP uses a two-stage filtering process: First, it applies Median Absolute Deviation (MAD) to initially remove outliers, then uses statistical features and clustering to separate honest from malicious updates before aggregating the global model. It also assigns a Trust Score (TS) to each participant based on how much their updates differ from the global model and then uses a genuine criterion to select honest clients by evaluating trust scores, update similarity, and deviation from the global model. Experimental results show that DT-BFL effectively defends against various poisoning attacks on datasets like MNIST, ToN-IoT, and CIFAR-10 using models such as CNN, MLP, ResNet, and DenseNet, and maintains high accuracy even when 50% of the clients are malicious. Using a permissioned blockchain further secures the system by enabling aggregation of the decentralized model and authentication of clients through smart contracts. The source code is available on https://github.com/UNSW-Canberra-2023/LUP . • We propose a framework called DT-BFL, which leverages decentralized edge intelligence, digital twins, federated learning, and permissioned blockchain to enhance edge intelligence’s efficiency, security, and reliability in IoT. • We propose LUP, a robust aggregation scheme for filtering malicious updates in federated learning. LUP utilizes two filters: one based on MAD of update norms and another employing statistical features and Agglomerative Hierarchical Clustering (AHC) to differentiate between honest and malicious updates. It also incorporates a genuine criterion to identify honest clients by evaluating their trust scores, model update similarity to the global model, and variance. Additionally, it introduces the Degree of Deviation (DoD) concept to assign trust scores (TS) to participants. LUP’s execution and validation occur decentralized via smart contracts and permissioned blockchain peers. • We conduct comprehensive experiments to assess the performance of the blockchain network and evaluate the robustness of LUP in defending against various poisoning attacks. Additionally, we compare LUP with recent aggregation schemes from the literature.