Federated learning is a distributed machine learning paradigm through centralized model aggregation. However, standard federated learning relies on a centralized server, making it vulnerable to server failures. While existing solutions utilize blockchain technology to implement Decentralized Federated Learning (DFL), the statistical heterogeneity of data distributions among clients severely degrades the performance of DFL. Driven by this issue, this paper proposes a decentralized federated prototype learning framework, named DFPL, which significantly improves the performance of DFL under heterogeneous data distributions. Specifically, DFPL introduces prototype learning into DFL to mitigate the impact of statistical heterogeneity and reduces the amount of parameters exchanged between clients. Additionally, blockchain is embedded into our framework, enabling the training and mining processes to be executed locally on each client. From a theoretical perspective, we analyze the convergence of DFPL by modeling the required computational resources during both training and mining. The experiment results highlight the superiority of DFPL in both model performance and communication efficiency across four benchmark datasets with heterogeneous data distributions.

Federated learning (FL), a distributed computing paradigm, is vulnerable to poisoning attacks that impair model performance and privacy attacks that leak participant information. Existing FL defense schemes struggle to counter poisoning attacks under data heterogeneity and high privacy computation overhead, limiting the practicality of federated learning. To address these issues, this paper proposes a model-contrastive federated learning framework with lightweight privacy preservation and poisoning attack detection, named MCFL. Specifically, we design a novel model-contrastive term by aligning intermediate-layer representations of models in the local optimization function to promote consistency of model updates among benign participants. Additionally, we design a secure aggregation protocol that adopts two-server aggregation instead of the single server to resist poisoning attacks with lightweight privacy protection. The proposed MCFL is theoretically proven in terms of convergence, robustness, and privacy. Extensive experiments demonstrate the superiority of MCFL compared to existing FL defense schemes.

The awareness of data privacy preservation in the Internet of Things (IoT) environment and the amount of IoT data production, are growing almost in parallel with each other. As a privacy-preserving framework, Federated Learning (FL) allows many participants to collaboratively build machine learning models while ensuring that their raw data remains local and undisclosed. However, as the devices charged in data collection are deployed in different IoT environments, we also face a significant challenge i.e., dealing with non-independently and identically distributed (non-IID) data. If the data is not distributed uniformly among the participants, it may lead to a significant performance degradation of the generated global model, which is far from the case when the data is distributed uniformly. To address this challenge, this study innovatively designs the Enhancing Federated Learning algorithm with Client-Specific Data Augmentation (FedSDA). The FedSDA matches clients by servers, and clients train local models using augmented datasets to overcome the negative influence mainly caused by non-IID, which consequently enhances the model accuracy. Our simulation experiments on the datasets Fashion-MNIST and CIFAR-10 ultimately demonstrate that FedSDA outperforms contemporary state-of-the-art FL strategies with similar design characteristics.

Cross-chain payment, serving as critical infrastructure for multi-chain ecosystem interoperability, confronts the fundamental challenge of simultaneously ensuring privacy preservation, regulatory compliance, and quantum-resistant security—objectives that are inherently difficult to reconcile. This paper proposes a Lattice-based Dynamic Privacy-preserving Cross-chain Payment Scheme (LDPCPS) that innovatively integrates advanced cryptographic primitives. Specifically, LDPCPS employs a privacy-preserving scalar product (PPSP) protocol enabling ciphertext-domain aggregation and verification, constructs a dynamic regulatory framework using signatures of knowledge (SoK) for zero-knowledge compliance proofs and risk-triggered traceability, and implements proxy re-encryption to facilitate seamless quantum-resistant key migration. Experimental results demonstrate that LDPCPS has significant superiority over state-of-the-art alternatives in quantum resistance, computational efficiency, and regulatory adaptability, thereby establishing a robust foundation for secure and compliant cross-chain transactions.

The combination of blockchain and Internet of Things technology has made significant progress in smart agriculture, which provides substantial support for data sharing and data privacy protection. Nevertheless, achieving efficient interactivity and privacy protection of agricultural data remains a crucial issues. To address the above problems, we propose a blockchain-assisted federated learning-driven support vector machine (BAFL-SVM) framework to realize efficient data sharing and privacy protection. The BAFL-SVM is composed of the FedSVM-RiceCare module and the FedPrivChain module. Specifically, in FedSVM-RiceCare, we utilize federated learning and SVM to train the model, improving the accuracy of the experiment. Then, in FedPrivChain, we adopt homomorphic encryption and a secret-sharing scheme to encrypt the local model parameters and upload them. Finally, we conduct a large number of experiments on a real-world dataset of rice pests and diseases, and the experimental results show that our framework not only guarantees the secure sharing of data but also achieves a higher recognition accuracy compared with other schemes.

As a distributed computing paradigm, federated learning (FL) enables multiple clients to cooperatively train in edge scenarios without sharing raw training data. Nonetheless, FL is vulnerable to Byzantine attacks due to its distributed nature. While numerous solutions have been proposed, they ignore the inconsistency of local models among clients caused by data heterogeneity (i.e., Non-IID), which severely degrades the performance of FL. Moreover, to further protect client privacy, complex security algorithms are integrated into FL, which seriously increases the privacy computation overhead on edge nodes. To tackle the above issues, this paper proposes a lightweight privacy-preserving federated learning framework, named LPP-FL, significantly improving the performance of FL against Byzantine attacks with Non-IID data. Specifically, we incorporate a correction-term into local model training to mitigate the inconsistency of local models among clients caused by data heterogeneity. Moreover, we design a secure protocol that is deployed on two servers, which achieves Byzantine-robust aggregation results while providing lightweight privacy protection for clients. Theoretical analysis demonstrates the security and robustness of LPP-FL. Extensive experiments show that LPP-FL exhibits superior performance against Byzantine attacks across various data distributions.

Federated learning is a powerful technique that enables collaborative learning among different clients. Prototype-based federated learning is a specific approach that improves the performance of local models by integrating class prototypes. However, prototype-based federated learning faces several challenges, such as prototype redundancy and prototype failure, which can limit its accuracy. In addition, it is also susceptible to poisoning attacks and server malfunction, which can degrade the quality of prototypes. To address these issues, we propose FedRFQ, a prototype-based federated learning approach that aims to reduce redundancy, minimize failure, and improve quality. FedRFQ leverages the SoftPool mechanism with prototype-based federated learning, which effectively mitigates prototype redundancy and prototype failure on Non-IID data. Moreover, we introduce the BFT-detect algorithm, a BFT detectable aggregation algorithm, to ensure the security of FedRFQ against poisoning attacks and server malfunction. Finally, we conducted experiments on three different datasets, namely MNIST, FEMNIST, and CIFAR-10. The results demonstrate that FedRFQ outperforms existing baselines in terms of accuracy when handling Non-IID data.

As one of the most widely used applications of the Internet of Things (IoT), intelligent transportation system (ITS) is of great significance for urban traffic planning, traffic control, and traffic guidance. However, widespread traffic congestion occurs with the increased number of vehicles. The traffic flow prediction is a good idea for traffic congestion. Therefore, many schemes have been proposed for accurate and real-time traffic flow prediction, but there still exist many issues, including low accuracy, weak adaptability and inferior real-time. Meanwhile, the complex spatial and temporal dependencies in traffic flow are still challenging. To address the above issues, we propose a novel spatial-temporal Chebyshev graph neural network model (ST-ChebNet) for traffic flow prediction to capture the spatial-temporal features, which can ensure accurate traffic flow prediction. Concretely, we first add a fully connected layer to fuse the features of traffic data into a new feature to generate a matrix, and then the long short-term memory (LSTM) model is adopted to learn traffic state changes for capturing the temporal dependencies. Then, we use the Chebyshev graph neural network (ChebNet) to learn the complex topological structures in the traffic network for capturing the spatial dependencies. Eventually, the spatial features and the temporal features are fused to guarantee the traffic flow prediction. The experiments show that ST-ChebNet can make accurate and real-time traffic flow prediction compared with other eight baseline methods on real-world traffic data sets PeMS.