Nowadays Practical Byzantine Fault Tolerance (PBFT) algorithm has become the most extensive consensus algorithm in the alliance chain. However, the PBFT algorithm is usually only applicable to small networks due to high communication complexity and poor scalability. Although there have been many improved algorithms for PBFT in recent years, they ignore fault tolerance and democracy. Therefore, to meet the requirements of a high degree of decentralization and fault tolerance of blockchain-based scenarios. This paper proposes a high fault tolerance consensus algorithm NBFT, which follows the principle of decentralization and democratization of blockchain and ensures the improvement of performance in fault tolerance upper limit and scalability. First, we use the consistent hash algorithm to group the consensus nodes to avoid much communication between nodes, reduce the communication complexity of the network, and improve the scalability of the network. Second, to ensure the fault-tolerant ability of the grouping consensus, the nodal decision broadcast model and threshold vote-counting model are proposed first. Combined with the proposed two models, the joint fault analysis of nodes is carried out, and the fault tolerance upper limit is more than 1/3. Then, the Faulty Number Determined (FND) model is introduced to simulate the experiment, and the results are verified.

Transformer-based methods have achieved excellent results in the field of time series forecasting due to their powerful ability to model sequences and capture their long-term dependencies. However, Transformer-based methods are still computationally inefficient and have high costs when modeling long sequences. In addition, previous work ignored the destruction of the original in-channel features by too many mixed features when performing channel mixing. To address the above issues, we introduce Mamba into the field of time series forecasting. The selective state-space model Mamba models long sequences more efficiently by expanding linearly according to the sequence length. Based on this, we propose Channel Mixing Mamba (CMMamba), which uses bidirectional Mamba to model sequences and uses a channel mixing mechanism to select appropriate mixed features to enhance the feature representation within the original channel. By introducing Mamba, we achieve efficient modeling of sequences. We also propose Deep Convolutional Structure (DCS) to learn cross-channel dependencies and temporal order information. Extensive experimental results on six real-world public datasets demonstrate the effectiveness of CMMamba.

The collaborative filtering algorithm based on the singular value decomposition plus plus (SVD++) model employs the linear interactions between the latent features of users and items to predict the rating in the recommendation systems. Aiming to further enrich the user model with explicit feedback, this paper proposes a user embedding model for rating prediction in SVD++-based collaborative filtering, named UE-SVD++. We exploit the user potential explicit feedback from the rating data and construct the user embedding matrix by the proposed user-wise mutual information values. In addition, the user embedding matrix is added to the existing user bias and implicit parameters in the SVD++ to increase the accuracy of the user modeling. Through extensive studies on four different datasets, we found that the rating prediction performance of the UE-SVD++ model is improved compared with other models, and the proposed model’s evaluation indicators root-mean-square error (RMSE) and mean absolute error (MAE) are decreased by 1.002–2.110% and 1.182–1.742%, respectively.

The Collaborative Filtering (CF) algorithm based on trust has been the main method used to solve the cold start problem in Recommendation Systems (RSs) for the past few years. Nevertheless, the current trust-based CF algorithm ignores the implicit influence contained in the ratings and trust data. In this paper, we propose a new rating prediction model named the Rating-Trust-based Recommendation Model (RTRM) to explore the influence of internal factors among the users. The proposed user internal factors include the user reliability and popularity. The internal factors derived from the explicit behavior data (ratings and trust), which can help us understand the user better and model the user more accurately. In addition, we incorporate the proposed internal factors into the Singular Value Decomposition Plus Plus (SVD + +) model to perform the rating prediction task. Experimental studies on two common datasets show that utilizing ratings and trust data simultaneously to mine the factors that influence the relationships among different users can improve the accuracy of rating prediction and effectively relieve the cold start problem.

As the first blockchain platform to support smart contracts, Ethereum has gained popularity and breeds various cybercrimes. Many phishing accounts on Ethereum take advantage of the blockchain’s anonymity to participate in illegal acts. To this end, to solve the transaction security problem caused by phishing accounts on Ethereum, this paper proposes a network embedding-based phishing account detection model. Firstly, we crawl the history of transactions from both labeled phishing and non-phishing accounts and use a new method to build these transactions as a transaction network, where each transaction edge is accompanied by additional transaction information for all source nodes of the target node. Then we propose a new random walk-based network embedding algorithm named bias2vec to obtain the embeddings of nodes as the feature inputs. Finally, we classify the accounts into phishing and non-phishing ones by different classifiers such as lightGBM and XGBoost. Experiments show that our proposed phishing account detection model achieves effective detection performance under different classifiers.