Nowadays, federated learning emerges as a new technique to preserve data privacy in distributed machine learning by limiting local data to the client and only aggregating model parameters from multiple parties on the server side. However, it also faces consequent threats from malicious clients, and some methods have been proposed without sufficient defense capability and efficient aggregation. To address these problems, we propose a novel aggregation algorithm, which incorporates PCA operation and clustering to select the excellent client in each round; and brings in a momentum-accelerated historical quality gradient-based approach to increase the weight when the performances of the global model are consistently degraded, which can achieve faster convergence on the basis of ensuring that the update direction of the global model is not manipulated by malicious nodes. Experimental results on the MNIST datasets show that our algorithm is only 0.93% lower than FedAvg under a no-attack scenario, and exhibits faster convergence compared to Krum, Multi-Krum, and Trimmed Mean Aggregation, and the accuracy improves 10.68%,35.83%,19.65% under Black-Box Edge Attack, Sign Flipping Attack, and Same Value Attack.
Nowadays privacy leakage related with big data spells big trouble for individuals. Generally, we provide data security and privacy protection through encrypted data but at the expense of usability. Fully homomorphic encryption allows to perform unlimited chaining of mathematical operations on encrypted data making it possible for some legal companies and institutions to use it. Compared to Gentry's scheme, fully homomorphic scheme over the integers can make complicated matters simplified but have not been widely applied due to the low efficiency. In this paper, a new improved FHE scheme based on DGHV scheme is proposed. We reduce the public key size significantly by introducing a pseudo-random number generator and encrypting with a cubic form rather than a linear form in the public key elements, which makes our scheme more efficient. Another part of our work is proving the scheme is semantically secure under the error-free approximate GCD problem. Finally, we propose a system model in purpose of illustrating the practical application of FHE scheme in big data.
In the networked control systems, control performance and network performance are closely related to the sampling period influenced by the network-induced delay. So in order to improve the network performance by adjusting the current sampling period, a period-vary sampling scheme is proposed based on an adjuster for the sampling period designed. In this scheme, the adjuster consists of a monitor, which acquires network resources utilization and the executive time of data packet, and a predictor, which uses BP neural network to predict the next sampling period by utilizing network resources utilization and data packet executive time. The simulation results show that the proposed scheme can alleviate the influence of time delay and improve the performance of the networked control systems.
Knowledge representation learning (knowledge graph embedding) plays a critical role in the application of knowledge graph construction. The multi-source information knowledge representation learning, which is one class of the most promising knowledge representation learning at present, mainly focuses on learning a large number of useful additional information of entities and relations in the knowledge graph into their embeddings, such as the text description information, entity type information, visual information, graph structure information, etc. However, there is a kind of simple but very common information — the number of an entity’s relations which means the number of an entity’s semantic types has been ignored. This work proposes a multi-source knowledge representation learning model KRL-NER, which embodies information of the number of an entity’s relations between entities into the entities’ embeddings through the attention mechanism. Specifically, first of all, we design and construct a submodel of the KRL-NER LearnNER which learns an embedding including the information on the number of an entity’s relations; then, we obtain a new embedding by exerting attention onto the embedding learned by the models such as TransE with this embedding; finally, we translate based onto the new embedding. Experiments, such as related tasks on knowledge graph: entity prediction, entity prediction under different relation types, and triple classification, are carried out to verify our model. The results show that our model is effective on the large-scale knowledge graphs, e.g. FB15K.
Feature selection is the first and essential step for dimension reduction in many application areas, such as data mining and machine learning, due to its computational efficiency and interpretability of the results. This paper focuses on feature selection methods based on information theory. By studying and analyzing the ideas and drawbacks of existing feature selection methods, it finds that in the process of feature selection separately focuses on a candidate feature its individual relationship with the predicted class vector may lead to some problems. And we believe that when the candidate feature is combined with the selected features, its comprehensive discriminative ability should be taken as the evaluation index of the candidate feature. Therefore, we propose a novel feature selection method in this paper. In the proposed method, we introduced the equivalent partition concept and adopted the mutual information gain maximize (MIGM) criterion to evaluate the candidate feature. In order to estimate the performance of MIGM, we conducted experiments on ten benchmark datasets and two different classifiers, k-Nearest Neighbor (KNN) and Naïve-Bayes (NB). Extensive experimental results demonstrate that our method can identify an effective feature subset that leads to better classification results than other methods.
A value chain optimizes the economic benefit of an enterprise alliance by integrating the cooperation relationships among the upstream and downstream companies. Nevertheless, the absence of information security mechanisms within the value chain limits the horizontal cooperation between competing enterprises. The paper proposes a scheme for building an enterprise value chain network based on an alliance blockchain. In the scheme, a distributed authentication technology and cross-chain transaction technology are introduced into the value chain, which enhances the security and reliability of value chain information and facilitates horizontal cooperation among companies. Using Hyperledger Fabric platform, we simulate and extensively evaluate an enterprise value chain network. Experimental results demonstrate the feasibility of the proposed scheme, which can serve as a guide for the construction of enterprise value chain networks in the real world.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)